Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2855 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4174. Min Range: -5.4174
Max Act: 5.4174. Min Act: -0.1700
Data Index: 3618387 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4174. Min Range: -5.4174
Max Act: 5.3236. Min Act: -0.1700
Data Index: 3678601 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4174. Min Range: -5.4174
Max Act: 5.2611. Min Act: -0.1700
Data Index: 3648462 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4174. Min Range: -5.4174
Max Act: 5.2299. Min Act: -0.1700
Data Index: 8454737 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4174. Min Range: -5.4174
Max Act: 5.2299. Min Act: -0.1700
Data Index: 6060171 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4174. Min Range: -5.4174
Max Act: 5.2299. Min Act: -0.1700
Data Index: 404723 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4174. Min Range: -5.4174
Max Act: 5.1674. Min Act: -0.1700
Data Index: 1151582 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4174. Min Range: -5.4174
Max Act: 5.1049. Min Act: -0.1700
Data Index: 2864006 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4174. Min Range: -5.4174
Max Act: 5.0736. Min Act: -0.1700
Data Index: 2468835 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4174. Min Range: -5.4174
Max Act: 5.0736. Min Act: -0.1700
Data Index: 3037545 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4174. Min Range: -5.4174
Max Act: 5.0736. Min Act: -0.1700
Data Index: 7148151 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4174. Min Range: -5.4174
Max Act: 5.0111. Min Act: -0.1700
Data Index: 8423455 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4174. Min Range: -5.4174
Max Act: 5.0111. Min Act: -0.1700
Data Index: 6316859 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4174. Min Range: -5.4174
Max Act: 5.0111. Min Act: -0.1700
Data Index: 7366226 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4174. Min Range: -5.4174
Max Act: 5.0111. Min Act: -0.1700
Data Index: 810443 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4174. Min Range: -5.4174
Max Act: 5.0424. Min Act: -0.1700
Data Index: 4243365 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4174. Min Range: -5.4174
Max Act: 4.9799. Min Act: -0.1700
Data Index: 7823001 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4174. Min Range: -5.4174
Max Act: 4.9799. Min Act: -0.1700
Data Index: 8346281 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4174. Min Range: -5.4174
Max Act: 4.9799. Min Act: -0.1700
Data Index: 324448 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4174. Min Range: -5.4174
Max Act: 4.9799. Min Act: -0.1700
Data Index: 2798494 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19