Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4802 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8439. Min Range: -6.8439
Max Act: 6.8439. Min Act: -0.1700
Data Index: 5342141 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8439. Min Range: -6.8439
Max Act: 6.8127. Min Act: -0.1700
Data Index: 7081648 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8439. Min Range: -6.8439
Max Act: 6.7189. Min Act: -0.1700
Data Index: 3650099 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8439. Min Range: -6.8439
Max Act: 6.7189. Min Act: -0.1700
Data Index: 7077098 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8439. Min Range: -6.8439
Max Act: 6.6877. Min Act: -0.1700
Data Index: 6777284 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8439. Min Range: -6.8439
Max Act: 6.6564. Min Act: -0.1700
Data Index: 6620405 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8439. Min Range: -6.8439
Max Act: 6.6877. Min Act: -0.1700
Data Index: 4520487 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8439. Min Range: -6.8439
Max Act: 6.6564. Min Act: -0.1700
Data Index: 3379008 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8439. Min Range: -6.8439
Max Act: 6.6564. Min Act: -0.1700
Data Index: 6519953 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8439. Min Range: -6.8439
Max Act: 6.6564. Min Act: -0.1700
Data Index: 1466775 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8439. Min Range: -6.8439
Max Act: 6.6564. Min Act: -0.1700
Data Index: 1548481 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8439. Min Range: -6.8439
Max Act: 6.6252. Min Act: -0.1700
Data Index: 2506732 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8439. Min Range: -6.8439
Max Act: 6.5939. Min Act: -0.1700
Data Index: 902045 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8439. Min Range: -6.8439
Max Act: 6.6252. Min Act: -0.1700
Data Index: 5567891 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8439. Min Range: -6.8439
Max Act: 6.6252. Min Act: -0.1700
Data Index: 1057914 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8439. Min Range: -6.8439
Max Act: 6.6252. Min Act: -0.1700
Data Index: 4873910 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8439. Min Range: -6.8439
Max Act: 6.6252. Min Act: -0.1700
Data Index: 4890534 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8439. Min Range: -6.8439
Max Act: 6.5939. Min Act: -0.1700
Data Index: 6638001 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8439. Min Range: -6.8439
Max Act: 6.5939. Min Act: -0.1700
Data Index: 1672481 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8439. Min Range: -6.8439
Max Act: 6.5939. Min Act: -0.1700
Data Index: 1928280 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19