Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1106 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6070. Min Range: -6.6070
Max Act: 6.6070. Min Act: -0.1700
Data Index: 8508390 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6070. Min Range: -6.6070
Max Act: 6.5445. Min Act: -0.1700
Data Index: 5829463 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6070. Min Range: -6.6070
Max Act: 6.5445. Min Act: -0.1700
Data Index: 1582373 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6070. Min Range: -6.6070
Max Act: 6.5445. Min Act: -0.1700
Data Index: 2236407 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6070. Min Range: -6.6070
Max Act: 6.4820. Min Act: -0.1700
Data Index: 2904448 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6070. Min Range: -6.6070
Max Act: 6.4820. Min Act: -0.1700
Data Index: 5233630 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6070. Min Range: -6.6070
Max Act: 6.4820. Min Act: -0.1700
Data Index: 1997793 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6070. Min Range: -6.6070
Max Act: 6.3882. Min Act: -0.1700
Data Index: 4187679 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6070. Min Range: -6.6070
Max Act: 6.3570. Min Act: -0.1700
Data Index: 58536 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6070. Min Range: -6.6070
Max Act: 6.3257. Min Act: -0.1700
Data Index: 2116453 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6070. Min Range: -6.6070
Max Act: 6.3257. Min Act: -0.1700
Data Index: 5012615 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6070. Min Range: -6.6070
Max Act: 6.3257. Min Act: -0.1700
Data Index: 2728088 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6070. Min Range: -6.6070
Max Act: 6.2632. Min Act: -0.1700
Data Index: 7482679 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6070. Min Range: -6.6070
Max Act: 6.2007. Min Act: -0.1700
Data Index: 3415350 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6070. Min Range: -6.6070
Max Act: 6.2320. Min Act: -0.1700
Data Index: 7256003 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6070. Min Range: -6.6070
Max Act: 6.2320. Min Act: -0.1700
Data Index: 863259 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6070. Min Range: -6.6070
Max Act: 6.2320. Min Act: -0.1700
Data Index: 3993250 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6070. Min Range: -6.6070
Max Act: 6.2007. Min Act: -0.1700
Data Index: 1505113 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6070. Min Range: -6.6070
Max Act: 6.2320. Min Act: -0.1700
Data Index: 3721941 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6070. Min Range: -6.6070
Max Act: 6.1695. Min Act: -0.1700
Data Index: 2958403 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19