Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3049 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1156. Min Range: -6.1156
Max Act: 6.1156. Min Act: -0.1700
Data Index: 2809867 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1156. Min Range: -6.1156
Max Act: 6.0531. Min Act: -0.1700
Data Index: 4796006 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.9593. Min Act: -0.1700
Data Index: 7421110 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.9281. Min Act: -0.1700
Data Index: 2809868 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.9281. Min Act: -0.1700
Data Index: 7971584 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.8968. Min Act: -0.1700
Data Index: 5456496 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.8968. Min Act: -0.1700
Data Index: 1061039 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.8968. Min Act: -0.1700
Data Index: 6808143 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.8656. Min Act: -0.1700
Data Index: 2809871 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.8968. Min Act: -0.1700
Data Index: 1550638 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.8656. Min Act: -0.1700
Data Index: 8520516 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.8656. Min Act: -0.1700
Data Index: 1271961 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.8656. Min Act: -0.1700
Data Index: 4820938 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.8656. Min Act: -0.1700
Data Index: 3528142 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.8656. Min Act: -0.1700
Data Index: 7206650 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.8656. Min Act: -0.1700
Data Index: 2404659 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.8656. Min Act: -0.1700
Data Index: 2809870 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.8656. Min Act: -0.1700
Data Index: 7500299 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.8343. Min Act: -0.1700
Data Index: 4886801 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1156. Min Range: -6.1156
Max Act: 5.8343. Min Act: -0.1700
Data Index: 1941787 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19