Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3330 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5750. Min Range: -5.5750
Max Act: 5.5750. Min Act: -0.1700
Data Index: 6949977 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5750. Min Range: -5.5750
Max Act: 5.5125. Min Act: -0.1700
Data Index: 1114309 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5750. Min Range: -5.5750
Max Act: 5.4500. Min Act: -0.1700
Data Index: 3292766 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5750. Min Range: -5.5750
Max Act: 5.3875. Min Act: -0.1700
Data Index: 552377 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5750. Min Range: -5.5750
Max Act: 5.4187. Min Act: -0.1700
Data Index: 1749663 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5750. Min Range: -5.5750
Max Act: 5.3875. Min Act: -0.1700
Data Index: 4807283 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5750. Min Range: -5.5750
Max Act: 5.3875. Min Act: -0.1700
Data Index: 1610510 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5750. Min Range: -5.5750
Max Act: 5.3875. Min Act: -0.1700
Data Index: 1929906 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5750. Min Range: -5.5750
Max Act: 5.3875. Min Act: -0.1700
Data Index: 2840669 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5750. Min Range: -5.5750
Max Act: 5.3562. Min Act: -0.1700
Data Index: 7953526 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5750. Min Range: -5.5750
Max Act: 5.3562. Min Act: -0.1700
Data Index: 8263422 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5750. Min Range: -5.5750
Max Act: 5.3562. Min Act: -0.1700
Data Index: 1176763 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5750. Min Range: -5.5750
Max Act: 5.3250. Min Act: -0.1700
Data Index: 5210233 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5750. Min Range: -5.5750
Max Act: 5.3250. Min Act: -0.1700
Data Index: 7099443 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5750. Min Range: -5.5750
Max Act: 5.3250. Min Act: -0.1700
Data Index: 3221233 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5750. Min Range: -5.5750
Max Act: 5.3250. Min Act: -0.1700
Data Index: 8574716 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5750. Min Range: -5.5750
Max Act: 5.2937. Min Act: -0.1700
Data Index: 1357056 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5750. Min Range: -5.5750
Max Act: 5.3250. Min Act: -0.1700
Data Index: 376699 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5750. Min Range: -5.5750
Max Act: 5.3250. Min Act: -0.1700
Data Index: 2546997 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5750. Min Range: -5.5750
Max Act: 5.3250. Min Act: -0.1700
Data Index: 3211020 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19