Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4897 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9307. Min Range: -10.9307
Max Act: 10.9307. Min Act: -0.1700
Data Index: 8064348 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9307. Min Range: -10.9307
Max Act: 10.6182. Min Act: -0.1700
Data Index: 7176827 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9307. Min Range: -10.9307
Max Act: 10.6182. Min Act: -0.1700
Data Index: 531371 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9307. Min Range: -10.9307
Max Act: 10.4932. Min Act: -0.1700
Data Index: 6324918 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9307. Min Range: -10.9307
Max Act: 10.4307. Min Act: -0.1700
Data Index: 7066921 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9307. Min Range: -10.9307
Max Act: 10.4307. Min Act: -0.1700
Data Index: 7358871 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9307. Min Range: -10.9307
Max Act: 10.4307. Min Act: -0.1700
Data Index: 1505342 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9307. Min Range: -10.9307
Max Act: 10.3682. Min Act: -0.1700
Data Index: 8091365 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9307. Min Range: -10.9307
Max Act: 10.3682. Min Act: -0.1700
Data Index: 1130454 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9307. Min Range: -10.9307
Max Act: 10.3057. Min Act: -0.1700
Data Index: 6877790 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9307. Min Range: -10.9307
Max Act: 10.3057. Min Act: -0.1700
Data Index: 2828278 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9307. Min Range: -10.9307
Max Act: 10.1807. Min Act: -0.1700
Data Index: 3016023 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9307. Min Range: -10.9307
Max Act: 10.2432. Min Act: -0.1700
Data Index: 595507 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9307. Min Range: -10.9307
Max Act: 10.2432. Min Act: -0.1700
Data Index: 2390149 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9307. Min Range: -10.9307
Max Act: 10.2432. Min Act: -0.1700
Data Index: 7937323 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9307. Min Range: -10.9307
Max Act: 10.2432. Min Act: -0.1699
Data Index: 6400344 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9307. Min Range: -10.9307
Max Act: 10.2432. Min Act: -0.1700
Data Index: 5313320 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9307. Min Range: -10.9307
Max Act: 10.1807. Min Act: -0.1700
Data Index: 288307 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9307. Min Range: -10.9307
Max Act: 10.1807. Min Act: -0.1700
Data Index: 5383094 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9307. Min Range: -10.9307
Max Act: 10.1807. Min Act: -0.1700
Data Index: 2835628 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19