Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6154 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1523. Min Range: -4.1523
Max Act: 4.1523. Min Act: -0.1700
Data Index: 4004467 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1523. Min Range: -4.1523
Max Act: 4.1523. Min Act: -0.1700
Data Index: 8407301 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1523. Min Range: -4.1523
Max Act: 4.0898. Min Act: -0.1700
Data Index: 1875991 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1523. Min Range: -4.1523
Max Act: 4.0586. Min Act: -0.1700
Data Index: 6526456 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1523. Min Range: -4.1523
Max Act: 4.0586. Min Act: -0.1700
Data Index: 4355754 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1523. Min Range: -4.1523
Max Act: 4.0273. Min Act: -0.1700
Data Index: 6311503 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1523. Min Range: -4.1523
Max Act: 4.0273. Min Act: -0.1700
Data Index: 4503901 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1523. Min Range: -4.1523
Max Act: 4.0273. Min Act: -0.1700
Data Index: 8585789 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1523. Min Range: -4.1523
Max Act: 4.0273. Min Act: -0.1700
Data Index: 3889375 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1523. Min Range: -4.1523
Max Act: 4.0273. Min Act: -0.1700
Data Index: 3246376 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1523. Min Range: -4.1523
Max Act: 3.9961. Min Act: -0.1700
Data Index: 1623672 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1523. Min Range: -4.1523
Max Act: 3.9961. Min Act: -0.1700
Data Index: 5655457 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1523. Min Range: -4.1523
Max Act: 3.9961. Min Act: -0.1700
Data Index: 5705336 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1523. Min Range: -4.1523
Max Act: 3.9961. Min Act: -0.1700
Data Index: 5933326 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1523. Min Range: -4.1523
Max Act: 3.9961. Min Act: -0.1700
Data Index: 3877415 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1523. Min Range: -4.1523
Max Act: 3.9648. Min Act: -0.1700
Data Index: 2882703 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1523. Min Range: -4.1523
Max Act: 3.9335. Min Act: -0.1700
Data Index: 7455642 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1523. Min Range: -4.1523
Max Act: 3.9961. Min Act: -0.1700
Data Index: 6151091 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1523. Min Range: -4.1523
Max Act: 3.9335. Min Act: -0.1700
Data Index: 6290296 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1523. Min Range: -4.1523
Max Act: 3.9335. Min Act: -0.1700
Data Index: 4006006 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19