Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2097 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3442. Min Range: -9.3442
Max Act: 9.3442. Min Act: -0.1700
Data Index: 1270107 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3442. Min Range: -9.3442
Max Act: 9.2817. Min Act: -0.1700
Data Index: 1350742 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3442. Min Range: -9.3442
Max Act: 9.1567. Min Act: -0.1700
Data Index: 7241089 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3442. Min Range: -9.3442
Max Act: 8.9692. Min Act: -0.1700
Data Index: 4619226 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3442. Min Range: -9.3442
Max Act: 8.9067. Min Act: -0.1700
Data Index: 8774158 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3442. Min Range: -9.3442
Max Act: 8.9067. Min Act: -0.1700
Data Index: 1987052 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3442. Min Range: -9.3442
Max Act: 8.8442. Min Act: -0.1700
Data Index: 3955210 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3442. Min Range: -9.3442
Max Act: 8.7192. Min Act: -0.1700
Data Index: 2819578 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3442. Min Range: -9.3442
Max Act: 8.7192. Min Act: -0.1700
Data Index: 4010754 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3442. Min Range: -9.3442
Max Act: 8.7192. Min Act: -0.1700
Data Index: 5246266 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3442. Min Range: -9.3442
Max Act: 8.7192. Min Act: -0.1700
Data Index: 7867711 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3442. Min Range: -9.3442
Max Act: 8.7192. Min Act: -0.1700
Data Index: 3029764 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3442. Min Range: -9.3442
Max Act: 8.7192. Min Act: -0.1700
Data Index: 274112 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3442. Min Range: -9.3442
Max Act: 8.6567. Min Act: -0.1700
Data Index: 8367264 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3442. Min Range: -9.3442
Max Act: 8.6567. Min Act: -0.1700
Data Index: 2019494 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3442. Min Range: -9.3442
Max Act: 8.6567. Min Act: -0.1700
Data Index: 5741135 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3442. Min Range: -9.3442
Max Act: 8.6567. Min Act: -0.1700
Data Index: 3049553 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3442. Min Range: -9.3442
Max Act: 8.6567. Min Act: -0.1700
Data Index: 5743405 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3442. Min Range: -9.3442
Max Act: 8.5942. Min Act: -0.1700
Data Index: 4385264 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3442. Min Range: -9.3442
Max Act: 8.5942. Min Act: -0.1700
Data Index: 1070421 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19