Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2396 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7435. Min Range: -8.7435
Max Act: 8.7435. Min Act: -0.1700
Data Index: 2219526 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7435. Min Range: -8.7435
Max Act: 8.2435. Min Act: -0.1700
Data Index: 2587773 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7435. Min Range: -8.7435
Max Act: 8.1810. Min Act: -0.1700
Data Index: 2809297 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7435. Min Range: -8.7435
Max Act: 8.1185. Min Act: -0.1700
Data Index: 5029699 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7435. Min Range: -8.7435
Max Act: 8.0872. Min Act: -0.1700
Data Index: 1289312 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7435. Min Range: -8.7435
Max Act: 8.0872. Min Act: -0.1700
Data Index: 233471 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7435. Min Range: -8.7435
Max Act: 8.0560. Min Act: -0.1700
Data Index: 96467 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7435. Min Range: -8.7435
Max Act: 7.9622. Min Act: -0.1700
Data Index: 1610046 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7435. Min Range: -8.7435
Max Act: 7.9622. Min Act: -0.1700
Data Index: 6348277 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7435. Min Range: -8.7435
Max Act: 7.9622. Min Act: -0.1700
Data Index: 1357803 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7435. Min Range: -8.7435
Max Act: 7.9622. Min Act: -0.1700
Data Index: 7994384 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7435. Min Range: -8.7435
Max Act: 7.9622. Min Act: -0.1700
Data Index: 3902784 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7435. Min Range: -8.7435
Max Act: 7.8685. Min Act: -0.1700
Data Index: 220507 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7435. Min Range: -8.7435
Max Act: 7.8997. Min Act: -0.1700
Data Index: 3546531 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7435. Min Range: -8.7435
Max Act: 7.8997. Min Act: -0.1700
Data Index: 4330207 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7435. Min Range: -8.7435
Max Act: 7.8685. Min Act: -0.1700
Data Index: 2068081 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7435. Min Range: -8.7435
Max Act: 7.8372. Min Act: -0.1700
Data Index: 5322415 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7435. Min Range: -8.7435
Max Act: 7.8372. Min Act: -0.1700
Data Index: 1007060 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7435. Min Range: -8.7435
Max Act: 7.8060. Min Act: -0.1700
Data Index: 3175176 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7435. Min Range: -8.7435
Max Act: 7.7747. Min Act: -0.1700
Data Index: 5018655 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19