Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1047 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7633. Min Range: -2.7633
Max Act: 2.7633. Min Act: -0.1700
Data Index: 1059151 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7633. Min Range: -2.7633
Max Act: 2.7313. Min Act: -0.1700
Data Index: 1879944 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7633. Min Range: -2.7633
Max Act: 2.7154. Min Act: -0.1700
Data Index: 1797902 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7633. Min Range: -2.7633
Max Act: 2.6833. Min Act: -0.1700
Data Index: 8704342 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7633. Min Range: -2.7633
Max Act: 2.6673. Min Act: -0.1700
Data Index: 2920323 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7633. Min Range: -2.7633
Max Act: 2.6673. Min Act: -0.1700
Data Index: 1177800 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7633. Min Range: -2.7633
Max Act: 2.6513. Min Act: -0.1700
Data Index: 6001093 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7633. Min Range: -2.7633
Max Act: 2.6352. Min Act: -0.1700
Data Index: 8576564 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7633. Min Range: -2.7633
Max Act: 2.6192. Min Act: -0.1700
Data Index: 3728262 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7633. Min Range: -2.7633
Max Act: 2.5870. Min Act: -0.1700
Data Index: 4811517 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7633. Min Range: -2.7633
Max Act: 2.6031. Min Act: -0.1700
Data Index: 8298 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7633. Min Range: -2.7633
Max Act: 2.5870. Min Act: -0.1700
Data Index: 5423234 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7633. Min Range: -2.7633
Max Act: 2.5870. Min Act: -0.1700
Data Index: 5099112 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7633. Min Range: -2.7633
Max Act: 2.5709. Min Act: -0.1700
Data Index: 397869 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7633. Min Range: -2.7633
Max Act: 2.5547. Min Act: -0.1700
Data Index: 1872542 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7633. Min Range: -2.7633
Max Act: 2.5547. Min Act: -0.1700
Data Index: 6813087 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7633. Min Range: -2.7633
Max Act: 2.5386. Min Act: -0.1700
Data Index: 7898238 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7633. Min Range: -2.7633
Max Act: 2.5386. Min Act: -0.1700
Data Index: 332425 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7633. Min Range: -2.7633
Max Act: 2.5386. Min Act: -0.1700
Data Index: 4629396 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7633. Min Range: -2.7633
Max Act: 2.5224. Min Act: -0.1700
Data Index: 601917 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19