Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4764 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0417. Min Range: -4.0417
Max Act: 4.0417. Min Act: -0.1700
Data Index: 800985 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0417. Min Range: -4.0417
Max Act: 4.0105. Min Act: -0.1700
Data Index: 3883760 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0417. Min Range: -4.0417
Max Act: 4.0105. Min Act: -0.1700
Data Index: 4737053 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0417. Min Range: -4.0417
Max Act: 3.9480. Min Act: -0.1700
Data Index: 988196 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0417. Min Range: -4.0417
Max Act: 3.9480. Min Act: -0.1700
Data Index: 3787912 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0417. Min Range: -4.0417
Max Act: 3.9167. Min Act: -0.1700
Data Index: 2416020 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0417. Min Range: -4.0417
Max Act: 3.8854. Min Act: -0.1700
Data Index: 7324935 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0417. Min Range: -4.0417
Max Act: 3.8854. Min Act: -0.1700
Data Index: 780981 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0417. Min Range: -4.0417
Max Act: 3.9480. Min Act: -0.1700
Data Index: 4590608 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0417. Min Range: -4.0417
Max Act: 3.8854. Min Act: -0.1700
Data Index: 2595639 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0417. Min Range: -4.0417
Max Act: 3.8854. Min Act: -0.1700
Data Index: 3883758 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0417. Min Range: -4.0417
Max Act: 3.8854. Min Act: -0.1700
Data Index: 7184086 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0417. Min Range: -4.0417
Max Act: 3.8854. Min Act: -0.1700
Data Index: 6394407 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0417. Min Range: -4.0417
Max Act: 3.8854. Min Act: -0.1700
Data Index: 3883757 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0417. Min Range: -4.0417
Max Act: 3.8542. Min Act: -0.1700
Data Index: 7041147 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0417. Min Range: -4.0417
Max Act: 3.8854. Min Act: -0.1700
Data Index: 8705538 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0417. Min Range: -4.0417
Max Act: 3.8542. Min Act: -0.1700
Data Index: 8295475 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0417. Min Range: -4.0417
Max Act: 3.8229. Min Act: -0.1700
Data Index: 4180445 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0417. Min Range: -4.0417
Max Act: 3.8229. Min Act: -0.1700
Data Index: 4126548 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0417. Min Range: -4.0417
Max Act: 3.7916. Min Act: -0.1700
Data Index: 3414849 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19