Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3579 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5179. Min Range: -5.5179
Max Act: 5.5179. Min Act: -0.1700
Data Index: 3528710 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5179. Min Range: -5.5179
Max Act: 5.4866. Min Act: -0.1700
Data Index: 1539162 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5179. Min Range: -5.5179
Max Act: 5.4866. Min Act: -0.1700
Data Index: 8333984 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5179. Min Range: -5.5179
Max Act: 5.4554. Min Act: -0.1700
Data Index: 8333983 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5179. Min Range: -5.5179
Max Act: 5.4554. Min Act: -0.1700
Data Index: 8333982 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5179. Min Range: -5.5179
Max Act: 5.3929. Min Act: -0.1700
Data Index: 2177159 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5179. Min Range: -5.5179
Max Act: 5.4241. Min Act: -0.1700
Data Index: 1759428 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5179. Min Range: -5.5179
Max Act: 5.4241. Min Act: -0.1700
Data Index: 4566945 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5179. Min Range: -5.5179
Max Act: 5.3929. Min Act: -0.1700
Data Index: 8333986 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5179. Min Range: -5.5179
Max Act: 5.3929. Min Act: -0.1700
Data Index: 613797 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5179. Min Range: -5.5179
Max Act: 5.3304. Min Act: -0.1700
Data Index: 2071747 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5179. Min Range: -5.5179
Max Act: 5.2991. Min Act: -0.1700
Data Index: 8032346 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5179. Min Range: -5.5179
Max Act: 5.2991. Min Act: -0.1700
Data Index: 1123281 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5179. Min Range: -5.5179
Max Act: 5.3304. Min Act: -0.1700
Data Index: 1013946 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5179. Min Range: -5.5179
Max Act: 5.3304. Min Act: -0.1700
Data Index: 7901371 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5179. Min Range: -5.5179
Max Act: 5.3304. Min Act: -0.1700
Data Index: 577082 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5179. Min Range: -5.5179
Max Act: 5.3304. Min Act: -0.1700
Data Index: 2524347 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5179. Min Range: -5.5179
Max Act: 5.3304. Min Act: -0.1700
Data Index: 8829245 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5179. Min Range: -5.5179
Max Act: 5.3304. Min Act: -0.1700
Data Index: 7361866 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5179. Min Range: -5.5179
Max Act: 5.2991. Min Act: -0.1700
Data Index: 1515494 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19