Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3009 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.5005. Min Act: -0.1700
Data Index: 2837982 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.5005. Min Act: -0.1700
Data Index: 7996983 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.3755. Min Act: -0.1700
Data Index: 1222236 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.3755. Min Act: -0.1700
Data Index: 2054528 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.3442. Min Act: -0.1700
Data Index: 1210067 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.3442. Min Act: -0.1700
Data Index: 8293801 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.2817. Min Act: -0.1700
Data Index: 8552616 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.2817. Min Act: -0.1700
Data Index: 326285 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.2192. Min Act: -0.1700
Data Index: 8469456 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.1880. Min Act: -0.1700
Data Index: 8375 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.1567. Min Act: -0.1700
Data Index: 4889554 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.1880. Min Act: -0.1700
Data Index: 6332321 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.1255. Min Act: -0.1700
Data Index: 3404554 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.1255. Min Act: -0.1700
Data Index: 7381258 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.0630. Min Act: -0.1700
Data Index: 5909968 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.0630. Min Act: -0.1700
Data Index: 2445792 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.0630. Min Act: -0.1700
Data Index: 7675573 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.0630. Min Act: -0.1700
Data Index: 4144383 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.0942. Min Act: -0.1700
Data Index: 6022713 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5005. Min Range: -8.5005
Max Act: 8.0005. Min Act: -0.1700
Data Index: 85043 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19