Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4205 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9555. Min Range: -3.9555
Max Act: 3.9555. Min Act: -0.1700
Data Index: 1667414 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9555. Min Range: -3.9555
Max Act: 3.9242. Min Act: -0.1700
Data Index: 7298499 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9555. Min Range: -3.9555
Max Act: 3.8930. Min Act: -0.1700
Data Index: 2457397 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9555. Min Range: -3.9555
Max Act: 3.8930. Min Act: -0.1700
Data Index: 2443452 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9555. Min Range: -3.9555
Max Act: 3.8930. Min Act: -0.1700
Data Index: 8713395 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9555. Min Range: -3.9555
Max Act: 3.8617. Min Act: -0.1700
Data Index: 871107 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9555. Min Range: -3.9555
Max Act: 3.8304. Min Act: -0.1700
Data Index: 8330852 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9555. Min Range: -3.9555
Max Act: 3.8617. Min Act: -0.1700
Data Index: 2002341 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9555. Min Range: -3.9555
Max Act: 3.8304. Min Act: -0.1700
Data Index: 2604895 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9555. Min Range: -3.9555
Max Act: 3.8304. Min Act: -0.1700
Data Index: 4367075 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9555. Min Range: -3.9555
Max Act: 3.7992. Min Act: -0.1700
Data Index: 2944459 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9555. Min Range: -3.9555
Max Act: 3.7679. Min Act: -0.1700
Data Index: 3167048 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9555. Min Range: -3.9555
Max Act: 3.7992. Min Act: -0.1700
Data Index: 7499780 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9555. Min Range: -3.9555
Max Act: 3.7992. Min Act: -0.1700
Data Index: 1142258 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9555. Min Range: -3.9555
Max Act: 3.7992. Min Act: -0.1700
Data Index: 7832046 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9555. Min Range: -3.9555
Max Act: 3.7992. Min Act: -0.1700
Data Index: 7940917 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9555. Min Range: -3.9555
Max Act: 3.8304. Min Act: -0.1700
Data Index: 2815842 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9555. Min Range: -3.9555
Max Act: 3.7679. Min Act: -0.1700
Data Index: 476045 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9555. Min Range: -3.9555
Max Act: 3.7679. Min Act: -0.1700
Data Index: 3534593 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9555. Min Range: -3.9555
Max Act: 3.7679. Min Act: -0.1700
Data Index: 4036330 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19