Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 95 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.6103. Min Act: -0.1700
Data Index: 1394763 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.4541. Min Act: -0.1700
Data Index: 2210256 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.4541. Min Act: -0.1697
Data Index: 3934345 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.3916. Min Act: -0.1700
Data Index: 7207310 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.3291. Min Act: -0.1700
Data Index: 6339731 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.3291. Min Act: -0.1700
Data Index: 1416728 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.2666. Min Act: -0.1700
Data Index: 8199913 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.2353. Min Act: -0.1700
Data Index: 7739351 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.2666. Min Act: -0.1700
Data Index: 4793955 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.2353. Min Act: -0.1700
Data Index: 6960646 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.2041. Min Act: -0.1700
Data Index: 5225473 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.1728. Min Act: -0.1700
Data Index: 1763024 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.2041. Min Act: -0.1700
Data Index: 2498165 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.2041. Min Act: -0.1700
Data Index: 4405097 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.2041. Min Act: -0.1699
Data Index: 1497750 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.1728. Min Act: -0.1700
Data Index: 4463202 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.1728. Min Act: -0.1700
Data Index: 5431679 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.1728. Min Act: -0.1700
Data Index: 2270825 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.1728. Min Act: -0.1700
Data Index: 2239793 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6103. Min Range: -5.6103
Max Act: 5.1728. Min Act: -0.1700
Data Index: 6958355 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19