Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2974 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1921. Min Range: -7.1921
Max Act: 7.1921. Min Act: -0.1700
Data Index: 647397 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.9733. Min Act: -0.1700
Data Index: 2316670 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1921. Min Range: -7.1921
Max Act: 7.0046. Min Act: -0.1700
Data Index: 8563356 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.9733. Min Act: -0.1700
Data Index: 6554938 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.8483. Min Act: -0.1700
Data Index: 28116 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.8171. Min Act: -0.1700
Data Index: 75757 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.7858. Min Act: -0.1700
Data Index: 4532387 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.7858. Min Act: -0.1700
Data Index: 5350356 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.8171. Min Act: -0.1700
Data Index: 2618759 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.7858. Min Act: -0.1700
Data Index: 4546872 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.7858. Min Act: -0.1700
Data Index: 6275606 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.7858. Min Act: -0.1700
Data Index: 75756 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.6921. Min Act: -0.1700
Data Index: 8227707 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.6608. Min Act: -0.1700
Data Index: 4931941 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.6921. Min Act: -0.1700
Data Index: 6695384 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.6608. Min Act: -0.1700
Data Index: 3708163 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.6608. Min Act: -0.1700
Data Index: 945696 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.6608. Min Act: -0.1700
Data Index: 6685173 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.6608. Min Act: -0.1700
Data Index: 6809213 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1921. Min Range: -7.1921
Max Act: 6.6296. Min Act: -0.1700
Data Index: 6947776 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19