Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4884 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7975. Min Range: -3.7975
Max Act: 3.7975. Min Act: -0.1700
Data Index: 5840790 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7975. Min Range: -3.7975
Max Act: 3.6411. Min Act: -0.1700
Data Index: 2590079 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7975. Min Range: -3.7975
Max Act: 3.6255. Min Act: -0.1700
Data Index: 2516342 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7975. Min Range: -3.7975
Max Act: 3.5942. Min Act: -0.1700
Data Index: 7520070 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7975. Min Range: -3.7975
Max Act: 3.5628. Min Act: -0.1700
Data Index: 3173864 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7975. Min Range: -3.7975
Max Act: 3.5472. Min Act: -0.1700
Data Index: 6807307 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7975. Min Range: -3.7975
Max Act: 3.5315. Min Act: -0.1700
Data Index: 2370986 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7975. Min Range: -3.7975
Max Act: 3.5159. Min Act: -0.1700
Data Index: 375791 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7975. Min Range: -3.7975
Max Act: 3.5002. Min Act: -0.1700
Data Index: 4597591 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7975. Min Range: -3.7975
Max Act: 3.4846. Min Act: -0.1700
Data Index: 1947935 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7975. Min Range: -3.7975
Max Act: 3.4846. Min Act: -0.1700
Data Index: 7096785 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7975. Min Range: -3.7975
Max Act: 3.4689. Min Act: -0.1700
Data Index: 6324577 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7975. Min Range: -3.7975
Max Act: 3.4689. Min Act: -0.1700
Data Index: 1764473 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7975. Min Range: -3.7975
Max Act: 3.4375. Min Act: -0.1700
Data Index: 4704192 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7975. Min Range: -3.7975
Max Act: 3.4375. Min Act: -0.1700
Data Index: 24910 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7975. Min Range: -3.7975
Max Act: 3.4532. Min Act: -0.1700
Data Index: 1496786 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7975. Min Range: -3.7975
Max Act: 3.4532. Min Act: -0.1700
Data Index: 8453427 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7975. Min Range: -3.7975
Max Act: 3.4375. Min Act: -0.1700
Data Index: 1326098 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7975. Min Range: -3.7975
Max Act: 3.4062. Min Act: -0.1700
Data Index: 7389832 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7975. Min Range: -3.7975
Max Act: 3.4219. Min Act: -0.1700
Data Index: 6149337 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19