Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2566 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.4343. Min Range: -10.4343
Max Act: 10.4343. Min Act: -0.1700
Data Index: 3718943 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4343. Min Range: -10.4343
Max Act: 10.4343. Min Act: -0.1700
Data Index: 2778945 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4343. Min Range: -10.4343
Max Act: 10.3093. Min Act: -0.1700
Data Index: 7112140 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4343. Min Range: -10.4343
Max Act: 10.3093. Min Act: -0.1700
Data Index: 8716909 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4343. Min Range: -10.4343
Max Act: 10.2468. Min Act: -0.1700
Data Index: 4362680 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4343. Min Range: -10.4343
Max Act: 10.1843. Min Act: -0.1700
Data Index: 3718947 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4343. Min Range: -10.4343
Max Act: 10.1843. Min Act: -0.1700
Data Index: 6114406 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4343. Min Range: -10.4343
Max Act: 10.1843. Min Act: -0.1700
Data Index: 1354759 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4343. Min Range: -10.4343
Max Act: 10.1843. Min Act: -0.1700
Data Index: 5909342 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4343. Min Range: -10.4343
Max Act: 10.1843. Min Act: -0.1700
Data Index: 3625107 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4343. Min Range: -10.4343
Max Act: 10.2468. Min Act: -0.1700
Data Index: 4409327 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4343. Min Range: -10.4343
Max Act: 10.0593. Min Act: -0.1700
Data Index: 197971 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4343. Min Range: -10.4343
Max Act: 10.1218. Min Act: -0.1700
Data Index: 5391490 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4343. Min Range: -10.4343
Max Act: 10.0593. Min Act: -0.1700
Data Index: 1282081 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4343. Min Range: -10.4343
Max Act: 10.0593. Min Act: -0.1700
Data Index: 6214479 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4343. Min Range: -10.4343
Max Act: 10.0593. Min Act: -0.1700
Data Index: 249274 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4343. Min Range: -10.4343
Max Act: 10.0593. Min Act: -0.1700
Data Index: 5905914 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4343. Min Range: -10.4343
Max Act: 9.9343. Min Act: -0.1700
Data Index: 620175 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4343. Min Range: -10.4343
Max Act: 9.9968. Min Act: -0.1700
Data Index: 3804531 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4343. Min Range: -10.4343
Max Act: 9.9968. Min Act: -0.1700
Data Index: 1401979 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19