Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5084 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9848. Min Range: -3.9848
Max Act: 3.9848. Min Act: -0.1700
Data Index: 3548603 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9848. Min Range: -3.9848
Max Act: 3.9535. Min Act: -0.1700
Data Index: 3407412 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9848. Min Range: -3.9848
Max Act: 3.9379. Min Act: -0.1700
Data Index: 4572166 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9848. Min Range: -3.9848
Max Act: 3.9223. Min Act: -0.1700
Data Index: 5273404 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9848. Min Range: -3.9848
Max Act: 3.9066. Min Act: -0.1700
Data Index: 613500 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9848. Min Range: -3.9848
Max Act: 3.8597. Min Act: -0.1700
Data Index: 3905747 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9848. Min Range: -3.9848
Max Act: 3.8128. Min Act: -0.1700
Data Index: 85160 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9848. Min Range: -3.9848
Max Act: 3.8128. Min Act: -0.1700
Data Index: 3111599 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9848. Min Range: -3.9848
Max Act: 3.7972. Min Act: -0.1700
Data Index: 3086676 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9848. Min Range: -3.9848
Max Act: 3.7503. Min Act: -0.1700
Data Index: 5138851 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9848. Min Range: -3.9848
Max Act: 3.7659. Min Act: -0.1700
Data Index: 8677601 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9848. Min Range: -3.9848
Max Act: 3.7503. Min Act: -0.1700
Data Index: 146543 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9848. Min Range: -3.9848
Max Act: 3.7346. Min Act: -0.1700
Data Index: 4402302 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9848. Min Range: -3.9848
Max Act: 3.7346. Min Act: -0.1700
Data Index: 5402791 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9848. Min Range: -3.9848
Max Act: 3.7346. Min Act: -0.1700
Data Index: 766098 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9848. Min Range: -3.9848
Max Act: 3.7033. Min Act: -0.1700
Data Index: 7392121 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9848. Min Range: -3.9848
Max Act: 3.7033. Min Act: -0.1700
Data Index: 800865 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9848. Min Range: -3.9848
Max Act: 3.7033. Min Act: -0.1700
Data Index: 1958823 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9848. Min Range: -3.9848
Max Act: 3.7033. Min Act: -0.1700
Data Index: 2806836 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9848. Min Range: -3.9848
Max Act: 3.7033. Min Act: -0.1700
Data Index: 2562532 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19