Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3393 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.6619. Min Act: -0.1700
Data Index: 7951961 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.5056. Min Act: -0.1700
Data Index: 6830262 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.3806. Min Act: -0.1700
Data Index: 1150142 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.3181. Min Act: -0.1700
Data Index: 3338462 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.3181. Min Act: -0.1700
Data Index: 8402102 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.2556. Min Act: -0.1700
Data Index: 2335926 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.2244. Min Act: -0.1700
Data Index: 2224132 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.2556. Min Act: -0.1700
Data Index: 2181742 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.1931. Min Act: -0.1700
Data Index: 7108054 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.1931. Min Act: -0.1700
Data Index: 4200826 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.1931. Min Act: -0.1700
Data Index: 3167770 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.1306. Min Act: -0.1700
Data Index: 5944864 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.1306. Min Act: -0.1700
Data Index: 4077647 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.1306. Min Act: -0.1700
Data Index: 142386 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.1306. Min Act: -0.1700
Data Index: 6729548 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.1306. Min Act: -0.1700
Data Index: 456643 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.0994. Min Act: -0.1700
Data Index: 4137708 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.1306. Min Act: -0.1700
Data Index: 5569390 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.0681. Min Act: -0.1700
Data Index: 3394735 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.0369. Min Act: -0.1700
Data Index: 7196020 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19