Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5731 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1378. Min Range: -8.1378
Max Act: 8.1378. Min Act: -0.1700
Data Index: 7592383 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1378. Min Range: -8.1378
Max Act: 8.0753. Min Act: -0.1700
Data Index: 6579638 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1378. Min Range: -8.1378
Max Act: 7.7316. Min Act: -0.1700
Data Index: 1598577 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1378. Min Range: -8.1378
Max Act: 7.4503. Min Act: -0.1700
Data Index: 1261954 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1378. Min Range: -8.1378
Max Act: 7.2316. Min Act: -0.1700
Data Index: 385120 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1378. Min Range: -8.1378
Max Act: 7.2003. Min Act: -0.1700
Data Index: 2103791 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1378. Min Range: -8.1378
Max Act: 7.0753. Min Act: -0.1700
Data Index: 5108648 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1378. Min Range: -8.1378
Max Act: 7.0441. Min Act: -0.1700
Data Index: 2558178 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1378. Min Range: -8.1378
Max Act: 7.0128. Min Act: -0.1700
Data Index: 2902324 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1378. Min Range: -8.1378
Max Act: 6.9816. Min Act: -0.1700
Data Index: 3850829 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1378. Min Range: -8.1378
Max Act: 6.9816. Min Act: -0.1700
Data Index: 6401600 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1378. Min Range: -8.1378
Max Act: 6.9816. Min Act: -0.1700
Data Index: 2810340 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1378. Min Range: -8.1378
Max Act: 6.9816. Min Act: -0.1700
Data Index: 5964755 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1378. Min Range: -8.1378
Max Act: 6.9191. Min Act: -0.1700
Data Index: 3039278 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1378. Min Range: -8.1378
Max Act: 6.9191. Min Act: -0.1700
Data Index: 4135456 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1378. Min Range: -8.1378
Max Act: 6.9191. Min Act: -0.1700
Data Index: 3602906 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1378. Min Range: -8.1378
Max Act: 6.9191. Min Act: -0.1700
Data Index: 2688071 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1378. Min Range: -8.1378
Max Act: 6.9191. Min Act: -0.1700
Data Index: 7910765 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1378. Min Range: -8.1378
Max Act: 6.8566. Min Act: -0.1700
Data Index: 3221011 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1378. Min Range: -8.1378
Max Act: 6.8878. Min Act: -0.1700
Data Index: 2878034 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19