Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4774 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5226. Min Range: -4.5226
Max Act: 4.5226. Min Act: -0.1700
Data Index: 377348 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5226. Min Range: -4.5226
Max Act: 4.5226. Min Act: -0.1700
Data Index: 3714581 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5226. Min Range: -4.5226
Max Act: 4.4288. Min Act: -0.1700
Data Index: 2485044 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5226. Min Range: -4.5226
Max Act: 4.4288. Min Act: -0.1700
Data Index: 2000411 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5226. Min Range: -4.5226
Max Act: 4.2725. Min Act: -0.1700
Data Index: 7850658 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5226. Min Range: -4.5226
Max Act: 4.2725. Min Act: -0.1700
Data Index: 4344434 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5226. Min Range: -4.5226
Max Act: 4.2413. Min Act: -0.1700
Data Index: 5283268 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5226. Min Range: -4.5226
Max Act: 4.2413. Min Act: -0.1700
Data Index: 177112 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5226. Min Range: -4.5226
Max Act: 4.2413. Min Act: -0.1700
Data Index: 3729899 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5226. Min Range: -4.5226
Max Act: 4.2100. Min Act: -0.1700
Data Index: 5414032 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5226. Min Range: -4.5226
Max Act: 4.1788. Min Act: -0.1700
Data Index: 1587410 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5226. Min Range: -4.5226
Max Act: 4.1475. Min Act: -0.1700
Data Index: 5452880 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5226. Min Range: -4.5226
Max Act: 4.2100. Min Act: -0.1700
Data Index: 177107 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5226. Min Range: -4.5226
Max Act: 4.1475. Min Act: -0.1700
Data Index: 6984099 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5226. Min Range: -4.5226
Max Act: 4.1475. Min Act: -0.1700
Data Index: 1694377 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5226. Min Range: -4.5226
Max Act: 4.1163. Min Act: -0.1700
Data Index: 751647 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5226. Min Range: -4.5226
Max Act: 4.0850. Min Act: -0.1700
Data Index: 1222212 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5226. Min Range: -4.5226
Max Act: 4.0850. Min Act: -0.1700
Data Index: 7146396 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5226. Min Range: -4.5226
Max Act: 4.0850. Min Act: -0.1700
Data Index: 751649 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5226. Min Range: -4.5226
Max Act: 4.0225. Min Act: -0.1700
Data Index: 6720309 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19