Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3384 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3170. Min Range: -4.3170
Max Act: 4.3170. Min Act: -0.1700
Data Index: 6143128 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3170. Min Range: -4.3170
Max Act: 4.2858. Min Act: -0.1700
Data Index: 3630170 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3170. Min Range: -4.3170
Max Act: 4.2545. Min Act: -0.1700
Data Index: 4622857 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3170. Min Range: -4.3170
Max Act: 4.2545. Min Act: -0.1700
Data Index: 1531337 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3170. Min Range: -4.3170
Max Act: 4.2233. Min Act: -0.1700
Data Index: 4326073 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3170. Min Range: -4.3170
Max Act: 4.2233. Min Act: -0.1700
Data Index: 8081282 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3170. Min Range: -4.3170
Max Act: 4.1920. Min Act: -0.1700
Data Index: 3953358 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3170. Min Range: -4.3170
Max Act: 4.1920. Min Act: -0.1700
Data Index: 2817749 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3170. Min Range: -4.3170
Max Act: 4.1920. Min Act: -0.1699
Data Index: 2922220 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3170. Min Range: -4.3170
Max Act: 4.1920. Min Act: -0.1700
Data Index: 7614160 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3170. Min Range: -4.3170
Max Act: 4.1608. Min Act: -0.1700
Data Index: 5343146 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3170. Min Range: -4.3170
Max Act: 4.1608. Min Act: -0.1700
Data Index: 6215003 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3170. Min Range: -4.3170
Max Act: 4.1608. Min Act: -0.1700
Data Index: 309313 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3170. Min Range: -4.3170
Max Act: 4.1608. Min Act: -0.1700
Data Index: 8520663 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3170. Min Range: -4.3170
Max Act: 4.1295. Min Act: -0.1700
Data Index: 7187976 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3170. Min Range: -4.3170
Max Act: 4.1295. Min Act: -0.1700
Data Index: 878477 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3170. Min Range: -4.3170
Max Act: 4.1295. Min Act: -0.1700
Data Index: 1348695 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3170. Min Range: -4.3170
Max Act: 4.0982. Min Act: -0.1700
Data Index: 1704887 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3170. Min Range: -4.3170
Max Act: 4.0982. Min Act: -0.1700
Data Index: 6343046 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3170. Min Range: -4.3170
Max Act: 4.0982. Min Act: -0.1700
Data Index: 4684158 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19