Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3794 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4128. Min Range: -4.4128
Max Act: 4.4128. Min Act: -0.1700
Data Index: 3662155 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4128. Min Range: -4.4128
Max Act: 4.4128. Min Act: -0.1700
Data Index: 8461820 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4128. Min Range: -4.4128
Max Act: 4.3503. Min Act: -0.1700
Data Index: 6355530 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4128. Min Range: -4.4128
Max Act: 4.3503. Min Act: -0.1700
Data Index: 1785840 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4128. Min Range: -4.4128
Max Act: 4.3190. Min Act: -0.1700
Data Index: 7663264 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4128. Min Range: -4.4128
Max Act: 4.3190. Min Act: -0.1700
Data Index: 1208328 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4128. Min Range: -4.4128
Max Act: 4.3190. Min Act: -0.1700
Data Index: 3428736 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4128. Min Range: -4.4128
Max Act: 4.2878. Min Act: -0.1700
Data Index: 8154117 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4128. Min Range: -4.4128
Max Act: 4.2878. Min Act: -0.1700
Data Index: 460606 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4128. Min Range: -4.4128
Max Act: 4.2565. Min Act: -0.1700
Data Index: 384876 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4128. Min Range: -4.4128
Max Act: 4.2565. Min Act: -0.1700
Data Index: 1976317 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4128. Min Range: -4.4128
Max Act: 4.2565. Min Act: -0.1700
Data Index: 24940 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4128. Min Range: -4.4128
Max Act: 4.2565. Min Act: -0.1700
Data Index: 4430033 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4128. Min Range: -4.4128
Max Act: 4.2565. Min Act: -0.1700
Data Index: 6785884 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4128. Min Range: -4.4128
Max Act: 4.2565. Min Act: -0.1700
Data Index: 6113971 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4128. Min Range: -4.4128
Max Act: 4.2878. Min Act: -0.1700
Data Index: 5790923 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4128. Min Range: -4.4128
Max Act: 4.2878. Min Act: -0.1700
Data Index: 4993853 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4128. Min Range: -4.4128
Max Act: 4.2565. Min Act: -0.1700
Data Index: 2093019 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4128. Min Range: -4.4128
Max Act: 4.2252. Min Act: -0.1700
Data Index: 1695957 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4128. Min Range: -4.4128
Max Act: 4.2252. Min Act: -0.1700
Data Index: 1747228 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19