Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4049 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.6843. Min Act: -0.1700
Data Index: 6805126 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.6531. Min Act: -0.1700
Data Index: 6270574 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.5593. Min Act: -0.1700
Data Index: 5098670 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.5593. Min Act: -0.1700
Data Index: 7611958 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.5593. Min Act: -0.1700
Data Index: 6546667 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.5281. Min Act: -0.1700
Data Index: 6546665 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.5281. Min Act: -0.1700
Data Index: 5319896 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.5281. Min Act: -0.1700
Data Index: 161874 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.4968. Min Act: -0.1700
Data Index: 2964513 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.4968. Min Act: -0.1700
Data Index: 8532997 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.4655. Min Act: -0.1700
Data Index: 691262 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.4655. Min Act: -0.1700
Data Index: 8819423 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.4655. Min Act: -0.1700
Data Index: 719256 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.4655. Min Act: -0.1700
Data Index: 202811 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.4030. Min Act: -0.1700
Data Index: 1097213 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.4343. Min Act: -0.1700
Data Index: 8254017 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.4030. Min Act: -0.1700
Data Index: 1193432 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.4030. Min Act: -0.1700
Data Index: 96566 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.4343. Min Act: -0.1700
Data Index: 828242 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6843. Min Range: -4.6843
Max Act: 4.3405. Min Act: -0.1700
Data Index: 447670 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19