Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5786 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2247. Min Range: -7.2247
Max Act: 7.2247. Min Act: -0.1700
Data Index: 1776170 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2247. Min Range: -7.2247
Max Act: 6.9435. Min Act: -0.1700
Data Index: 8087040 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2247. Min Range: -7.2247
Max Act: 6.8497. Min Act: -0.1700
Data Index: 7110167 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2247. Min Range: -7.2247
Max Act: 6.7560. Min Act: -0.1700
Data Index: 6906218 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2247. Min Range: -7.2247
Max Act: 6.7247. Min Act: -0.1700
Data Index: 7238005 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2247. Min Range: -7.2247
Max Act: 6.5685. Min Act: -0.1700
Data Index: 2471258 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2247. Min Range: -7.2247
Max Act: 6.5685. Min Act: -0.1700
Data Index: 1148607 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2247. Min Range: -7.2247
Max Act: 6.5685. Min Act: -0.1700
Data Index: 384329 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2247. Min Range: -7.2247
Max Act: 6.5685. Min Act: -0.1700
Data Index: 4642824 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2247. Min Range: -7.2247
Max Act: 6.5372. Min Act: -0.1700
Data Index: 6314256 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2247. Min Range: -7.2247
Max Act: 6.5060. Min Act: -0.1700
Data Index: 192253 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2247. Min Range: -7.2247
Max Act: 6.4747. Min Act: -0.1700
Data Index: 3329856 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2247. Min Range: -7.2247
Max Act: 6.5060. Min Act: -0.1700
Data Index: 2562146 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2247. Min Range: -7.2247
Max Act: 6.4747. Min Act: -0.1700
Data Index: 1939030 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2247. Min Range: -7.2247
Max Act: 6.4747. Min Act: -0.1700
Data Index: 7916821 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2247. Min Range: -7.2247
Max Act: 6.4747. Min Act: -0.1700
Data Index: 8317165 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2247. Min Range: -7.2247
Max Act: 6.4435. Min Act: -0.1700
Data Index: 3018096 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2247. Min Range: -7.2247
Max Act: 6.4435. Min Act: -0.1700
Data Index: 1801555 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2247. Min Range: -7.2247
Max Act: 6.4122. Min Act: -0.1700
Data Index: 6956331 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2247. Min Range: -7.2247
Max Act: 6.4435. Min Act: -0.1700
Data Index: 5790748 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19