Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3415 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3242. Min Range: -4.3242
Max Act: 4.3242. Min Act: -0.1700
Data Index: 4699706 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3242. Min Range: -4.3242
Max Act: 3.9804. Min Act: -0.1700
Data Index: 8579821 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3242. Min Range: -4.3242
Max Act: 3.9804. Min Act: -0.1700
Data Index: 100816 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3242. Min Range: -4.3242
Max Act: 3.9492. Min Act: -0.1700
Data Index: 617367 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3242. Min Range: -4.3242
Max Act: 3.9492. Min Act: -0.1700
Data Index: 3430531 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3242. Min Range: -4.3242
Max Act: 3.9492. Min Act: -0.1700
Data Index: 6074718 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3242. Min Range: -4.3242
Max Act: 3.9179. Min Act: -0.1700
Data Index: 6552378 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3242. Min Range: -4.3242
Max Act: 3.9179. Min Act: -0.1700
Data Index: 4734341 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3242. Min Range: -4.3242
Max Act: 3.8866. Min Act: -0.1700
Data Index: 1256070 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3242. Min Range: -4.3242
Max Act: 3.8554. Min Act: -0.1700
Data Index: 7391713 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3242. Min Range: -4.3242
Max Act: 3.8554. Min Act: -0.1700
Data Index: 5278447 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3242. Min Range: -4.3242
Max Act: 3.8241. Min Act: -0.1700
Data Index: 3536059 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3242. Min Range: -4.3242
Max Act: 3.8554. Min Act: -0.1700
Data Index: 7019291 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3242. Min Range: -4.3242
Max Act: 3.8554. Min Act: -0.1700
Data Index: 6552380 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3242. Min Range: -4.3242
Max Act: 3.8554. Min Act: -0.1700
Data Index: 5561061 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3242. Min Range: -4.3242
Max Act: 3.8554. Min Act: -0.1700
Data Index: 1383338 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3242. Min Range: -4.3242
Max Act: 3.8554. Min Act: -0.1700
Data Index: 4318251 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3242. Min Range: -4.3242
Max Act: 3.8241. Min Act: -0.1700
Data Index: 5360554 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3242. Min Range: -4.3242
Max Act: 3.8554. Min Act: -0.1700
Data Index: 2077810 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3242. Min Range: -4.3242
Max Act: 3.8554. Min Act: -0.1700
Data Index: 2069824 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19