Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2645 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5275. Min Range: -5.5275
Max Act: 5.5275. Min Act: -0.1700
Data Index: 339383 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5275. Min Range: -5.5275
Max Act: 5.1837. Min Act: -0.1700
Data Index: 4210587 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5275. Min Range: -5.5275
Max Act: 5.0900. Min Act: -0.1700
Data Index: 336559 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5275. Min Range: -5.5275
Max Act: 5.0900. Min Act: -0.1700
Data Index: 6341113 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5275. Min Range: -5.5275
Max Act: 5.0587. Min Act: -0.1700
Data Index: 5953892 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5275. Min Range: -5.5275
Max Act: 5.0275. Min Act: -0.1700
Data Index: 1410241 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5275. Min Range: -5.5275
Max Act: 4.9962. Min Act: -0.1700
Data Index: 7138963 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5275. Min Range: -5.5275
Max Act: 4.9337. Min Act: -0.1700
Data Index: 2356427 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5275. Min Range: -5.5275
Max Act: 4.8712. Min Act: -0.1700
Data Index: 3516838 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5275. Min Range: -5.5275
Max Act: 4.8712. Min Act: -0.1700
Data Index: 4052844 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5275. Min Range: -5.5275
Max Act: 4.8712. Min Act: -0.1700
Data Index: 4777395 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5275. Min Range: -5.5275
Max Act: 4.8712. Min Act: -0.1700
Data Index: 6134075 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5275. Min Range: -5.5275
Max Act: 4.8400. Min Act: -0.1700
Data Index: 5311571 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5275. Min Range: -5.5275
Max Act: 4.8400. Min Act: -0.1700
Data Index: 775093 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5275. Min Range: -5.5275
Max Act: 4.8400. Min Act: -0.1700
Data Index: 2123379 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5275. Min Range: -5.5275
Max Act: 4.7775. Min Act: -0.1700
Data Index: 2919227 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5275. Min Range: -5.5275
Max Act: 4.8400. Min Act: -0.1700
Data Index: 8451882 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5275. Min Range: -5.5275
Max Act: 4.7775. Min Act: -0.1700
Data Index: 7145577 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5275. Min Range: -5.5275
Max Act: 4.7775. Min Act: -0.1700
Data Index: 4241746 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5275. Min Range: -5.5275
Max Act: 4.7775. Min Act: -0.1700
Data Index: 8051076 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19