Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5219 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8384. Min Range: -7.8384
Max Act: 7.8384. Min Act: -0.1700
Data Index: 2606535 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8384. Min Range: -7.8384
Max Act: 7.7446. Min Act: -0.1700
Data Index: 5075436 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8384. Min Range: -7.8384
Max Act: 7.7446. Min Act: -0.1700
Data Index: 8515736 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8384. Min Range: -7.8384
Max Act: 7.5884. Min Act: -0.1700
Data Index: 4379347 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8384. Min Range: -7.8384
Max Act: 7.5571. Min Act: -0.1700
Data Index: 4351493 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8384. Min Range: -7.8384
Max Act: 7.4009. Min Act: -0.1700
Data Index: 2777798 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8384. Min Range: -7.8384
Max Act: 7.3696. Min Act: -0.1700
Data Index: 2629990 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8384. Min Range: -7.8384
Max Act: 7.3696. Min Act: -0.1700
Data Index: 8400940 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8384. Min Range: -7.8384
Max Act: 7.3384. Min Act: -0.1700
Data Index: 4645576 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8384. Min Range: -7.8384
Max Act: 7.3071. Min Act: -0.1700
Data Index: 7226747 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8384. Min Range: -7.8384
Max Act: 7.3384. Min Act: -0.1700
Data Index: 8703896 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8384. Min Range: -7.8384
Max Act: 7.2759. Min Act: -0.1700
Data Index: 546990 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8384. Min Range: -7.8384
Max Act: 7.2759. Min Act: -0.1700
Data Index: 1060513 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8384. Min Range: -7.8384
Max Act: 7.2446. Min Act: -0.1700
Data Index: 816860 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8384. Min Range: -7.8384
Max Act: 7.2446. Min Act: -0.1700
Data Index: 3783197 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8384. Min Range: -7.8384
Max Act: 7.2446. Min Act: -0.1700
Data Index: 816859 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8384. Min Range: -7.8384
Max Act: 7.1821. Min Act: -0.1700
Data Index: 5349141 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8384. Min Range: -7.8384
Max Act: 7.2134. Min Act: -0.1700
Data Index: 6454966 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8384. Min Range: -7.8384
Max Act: 7.2134. Min Act: -0.1700
Data Index: 816858 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8384. Min Range: -7.8384
Max Act: 7.1821. Min Act: -0.1700
Data Index: 6656918 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19