Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4353 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.4745. Min Act: -0.1700
Data Index: 6803508 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.4120. Min Act: -0.1700
Data Index: 4513932 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.3808. Min Act: -0.1700
Data Index: 7432612 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.2870. Min Act: -0.1700
Data Index: 1245330 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.2245. Min Act: -0.1700
Data Index: 6369086 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.2245. Min Act: -0.1700
Data Index: 2526530 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.2245. Min Act: -0.1700
Data Index: 2692861 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.2245. Min Act: -0.1700
Data Index: 2093141 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.1933. Min Act: -0.1700
Data Index: 6369088 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.2245. Min Act: -0.1700
Data Index: 44251 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.1307. Min Act: -0.1700
Data Index: 680444 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.1307. Min Act: -0.1700
Data Index: 1245328 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.1620. Min Act: -0.1700
Data Index: 8825610 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.1620. Min Act: -0.1700
Data Index: 2526519 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.1307. Min Act: -0.1700
Data Index: 6069400 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.1307. Min Act: -0.1700
Data Index: 7001537 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.1307. Min Act: -0.1700
Data Index: 4490911 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.0995. Min Act: -0.1700
Data Index: 2526527 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.1307. Min Act: -0.1700
Data Index: 8458562 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4745. Min Range: -4.4745
Max Act: 4.1307. Min Act: -0.1700
Data Index: 863060 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19