Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 0 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6814. Min Range: -7.6814
Max Act: 7.6814. Min Act: -0.1700
Data Index: 2593869 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6814. Min Range: -7.6814
Max Act: 7.4939. Min Act: -0.1700
Data Index: 4393016 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6814. Min Range: -7.6814
Max Act: 7.4939. Min Act: -0.1700
Data Index: 8354925 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6814. Min Range: -7.6814
Max Act: 7.4939. Min Act: -0.1700
Data Index: 3028455 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6814. Min Range: -7.6814
Max Act: 7.4314. Min Act: -0.1700
Data Index: 8637400 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6814. Min Range: -7.6814
Max Act: 7.3689. Min Act: -0.1700
Data Index: 7452339 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6814. Min Range: -7.6814
Max Act: 7.4002. Min Act: -0.1700
Data Index: 4751431 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6814. Min Range: -7.6814
Max Act: 7.4002. Min Act: -0.1700
Data Index: 1144517 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6814. Min Range: -7.6814
Max Act: 7.3689. Min Act: -0.1700
Data Index: 6655416 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6814. Min Range: -7.6814
Max Act: 7.3689. Min Act: -0.1700
Data Index: 398587 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6814. Min Range: -7.6814
Max Act: 7.3689. Min Act: -0.1700
Data Index: 914987 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6814. Min Range: -7.6814
Max Act: 7.3689. Min Act: -0.1700
Data Index: 3553537 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6814. Min Range: -7.6814
Max Act: 7.3377. Min Act: -0.1700
Data Index: 2178827 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6814. Min Range: -7.6814
Max Act: 7.3377. Min Act: -0.1700
Data Index: 3488257 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6814. Min Range: -7.6814
Max Act: 7.3064. Min Act: -0.1700
Data Index: 1283438 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6814. Min Range: -7.6814
Max Act: 7.2752. Min Act: -0.1700
Data Index: 6524610 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6814. Min Range: -7.6814
Max Act: 7.2752. Min Act: -0.1700
Data Index: 7471837 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6814. Min Range: -7.6814
Max Act: 7.2439. Min Act: -0.1700
Data Index: 801785 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6814. Min Range: -7.6814
Max Act: 7.2127. Min Act: -0.1700
Data Index: 4520288 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6814. Min Range: -7.6814
Max Act: 7.2439. Min Act: -0.1700
Data Index: 2374540 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19