Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1817 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9105. Min Range: -2.9105
Max Act: 2.9105. Min Act: -0.1700
Data Index: 2652375 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9105. Min Range: -2.9105
Max Act: 2.8946. Min Act: -0.1700
Data Index: 6161046 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9105. Min Range: -2.9105
Max Act: 2.8629. Min Act: -0.1700
Data Index: 6897797 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9105. Min Range: -2.9105
Max Act: 2.7993. Min Act: -0.1700
Data Index: 6103850 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9105. Min Range: -2.9105
Max Act: 2.7993. Min Act: -0.1700
Data Index: 2743772 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9105. Min Range: -2.9105
Max Act: 2.7674. Min Act: -0.1700
Data Index: 3414319 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9105. Min Range: -2.9105
Max Act: 2.7993. Min Act: -0.1700
Data Index: 6626402 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9105. Min Range: -2.9105
Max Act: 2.7515. Min Act: -0.1700
Data Index: 799423 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9105. Min Range: -2.9105
Max Act: 2.7515. Min Act: -0.1700
Data Index: 5106551 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9105. Min Range: -2.9105
Max Act: 2.7355. Min Act: -0.1700
Data Index: 3869841 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9105. Min Range: -2.9105
Max Act: 2.7355. Min Act: -0.1700
Data Index: 2546162 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9105. Min Range: -2.9105
Max Act: 2.7035. Min Act: -0.1700
Data Index: 4282116 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9105. Min Range: -2.9105
Max Act: 2.6875. Min Act: -0.1700
Data Index: 6568372 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9105. Min Range: -2.9105
Max Act: 2.6875. Min Act: -0.1700
Data Index: 5314122 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9105. Min Range: -2.9105
Max Act: 2.6875. Min Act: -0.1700
Data Index: 2778192 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9105. Min Range: -2.9105
Max Act: 2.6555. Min Act: -0.1700
Data Index: 2703771 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9105. Min Range: -2.9105
Max Act: 2.6715. Min Act: -0.1700
Data Index: 7212103 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9105. Min Range: -2.9105
Max Act: 2.6875. Min Act: -0.1700
Data Index: 8401313 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9105. Min Range: -2.9105
Max Act: 2.6715. Min Act: -0.1700
Data Index: 891918 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9105. Min Range: -2.9105
Max Act: 2.6555. Min Act: -0.1700
Data Index: 5052143 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19