Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5116 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1945. Min Range: -6.1945
Max Act: 6.1945. Min Act: -0.1700
Data Index: 8537781 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1945. Min Range: -6.1945
Max Act: 6.1320. Min Act: -0.1700
Data Index: 7185868 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1945. Min Range: -6.1945
Max Act: 6.1320. Min Act: -0.1700
Data Index: 5043387 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1945. Min Range: -6.1945
Max Act: 6.0695. Min Act: -0.1700
Data Index: 4117779 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1945. Min Range: -6.1945
Max Act: 6.0070. Min Act: -0.1700
Data Index: 2691524 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1945. Min Range: -6.1945
Max Act: 6.0070. Min Act: -0.1700
Data Index: 7666120 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1945. Min Range: -6.1945
Max Act: 5.9445. Min Act: -0.1700
Data Index: 8707463 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1945. Min Range: -6.1945
Max Act: 5.9445. Min Act: -0.1700
Data Index: 3365157 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1945. Min Range: -6.1945
Max Act: 5.9445. Min Act: -0.1700
Data Index: 5686288 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1945. Min Range: -6.1945
Max Act: 5.9133. Min Act: -0.1700
Data Index: 505289 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1945. Min Range: -6.1945
Max Act: 5.9133. Min Act: -0.1700
Data Index: 3580879 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1945. Min Range: -6.1945
Max Act: 5.8820. Min Act: -0.1700
Data Index: 7185869 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1945. Min Range: -6.1945
Max Act: 5.8820. Min Act: -0.1700
Data Index: 4501357 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1945. Min Range: -6.1945
Max Act: 5.8508. Min Act: -0.1700
Data Index: 8347635 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1945. Min Range: -6.1945
Max Act: 5.8820. Min Act: -0.1700
Data Index: 6026604 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1945. Min Range: -6.1945
Max Act: 5.8508. Min Act: -0.1700
Data Index: 4461505 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1945. Min Range: -6.1945
Max Act: 5.8195. Min Act: -0.1700
Data Index: 3770326 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1945. Min Range: -6.1945
Max Act: 5.8508. Min Act: -0.1700
Data Index: 8629268 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1945. Min Range: -6.1945
Max Act: 5.8508. Min Act: -0.1700
Data Index: 4875430 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1945. Min Range: -6.1945
Max Act: 5.8195. Min Act: -0.1700
Data Index: 6917846 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19