Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3157 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1525. Min Range: -7.1525
Max Act: 7.1525. Min Act: -0.1700
Data Index: 1474412 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1525. Min Range: -7.1525
Max Act: 7.0588. Min Act: -0.1700
Data Index: 890972 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1525. Min Range: -7.1525
Max Act: 7.0588. Min Act: -0.1700
Data Index: 7776732 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1525. Min Range: -7.1525
Max Act: 7.0588. Min Act: -0.1700
Data Index: 4476133 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1525. Min Range: -7.1525
Max Act: 6.9650. Min Act: -0.1700
Data Index: 7025699 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1525. Min Range: -7.1525
Max Act: 6.9963. Min Act: -0.1700
Data Index: 1723657 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1525. Min Range: -7.1525
Max Act: 6.9025. Min Act: -0.1700
Data Index: 452542 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1525. Min Range: -7.1525
Max Act: 6.8088. Min Act: -0.1700
Data Index: 8420692 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1525. Min Range: -7.1525
Max Act: 6.8400. Min Act: -0.1700
Data Index: 7692246 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1525. Min Range: -7.1525
Max Act: 6.7463. Min Act: -0.1700
Data Index: 439797 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1525. Min Range: -7.1525
Max Act: 6.7775. Min Act: -0.1700
Data Index: 8682355 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1525. Min Range: -7.1525
Max Act: 6.7463. Min Act: -0.1700
Data Index: 1062859 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1525. Min Range: -7.1525
Max Act: 6.7775. Min Act: -0.1700
Data Index: 1894561 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1525. Min Range: -7.1525
Max Act: 6.7150. Min Act: -0.1700
Data Index: 214218 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1525. Min Range: -7.1525
Max Act: 6.6838. Min Act: -0.1700
Data Index: 6613934 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1525. Min Range: -7.1525
Max Act: 6.6838. Min Act: -0.1700
Data Index: 6528257 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1525. Min Range: -7.1525
Max Act: 6.6838. Min Act: -0.1700
Data Index: 327553 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1525. Min Range: -7.1525
Max Act: 6.6838. Min Act: -0.1700
Data Index: 6121882 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1525. Min Range: -7.1525
Max Act: 6.6838. Min Act: -0.1700
Data Index: 7810073 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1525. Min Range: -7.1525
Max Act: 6.6838. Min Act: -0.1700
Data Index: 3202661 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #19