Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5479 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.9899. Min Act: -0.1700
Data Index: 8301240 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.9586. Min Act: -0.1700
Data Index: 7393019 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.9274. Min Act: -0.1700
Data Index: 7316257 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.9274. Min Act: -0.1700
Data Index: 5749094 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.8961. Min Act: -0.1700
Data Index: 3866629 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.8649. Min Act: -0.1700
Data Index: 3982860 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.8649. Min Act: -0.1700
Data Index: 2412645 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.8336. Min Act: -0.1700
Data Index: 102583 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.8336. Min Act: -0.1700
Data Index: 7412491 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.8336. Min Act: -0.1700
Data Index: 6602194 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.8336. Min Act: -0.1700
Data Index: 6208352 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.8336. Min Act: -0.1700
Data Index: 5749093 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.8024. Min Act: -0.1700
Data Index: 5283185 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.8336. Min Act: -0.1700
Data Index: 4596839 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.8336. Min Act: -0.1700
Data Index: 4277677 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.8336. Min Act: -0.1700
Data Index: 2577512 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.8336. Min Act: -0.1700
Data Index: 652693 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.8336. Min Act: -0.1700
Data Index: 6630396 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.7711. Min Act: -0.1700
Data Index: 1392028 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9899. Min Range: -4.9899
Max Act: 4.8024. Min Act: -0.1700
Data Index: 2460760 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19