Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4891 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0530. Min Range: -5.0530
Max Act: 5.0530. Min Act: -0.1700
Data Index: 888709 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.8967. Min Act: -0.1700
Data Index: 4244279 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.7405. Min Act: -0.1700
Data Index: 478862 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.6155. Min Act: -0.1700
Data Index: 5993173 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.5842. Min Act: -0.1700
Data Index: 920231 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.5842. Min Act: -0.1700
Data Index: 7192649 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.5530. Min Act: -0.1700
Data Index: 3763124 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.5530. Min Act: -0.1700
Data Index: 7700480 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.4905. Min Act: -0.1700
Data Index: 1257537 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.5217. Min Act: -0.1700
Data Index: 5907328 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.5217. Min Act: -0.1700
Data Index: 8195648 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.4905. Min Act: -0.1700
Data Index: 4490366 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.4592. Min Act: -0.1700
Data Index: 1191106 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.4592. Min Act: -0.1700
Data Index: 7620770 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.4280. Min Act: -0.1700
Data Index: 5086445 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.4280. Min Act: -0.1700
Data Index: 3823012 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.3967. Min Act: -0.1700
Data Index: 5162320 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.3967. Min Act: -0.1700
Data Index: 4369326 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.3967. Min Act: -0.1700
Data Index: 7577640 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0530. Min Range: -5.0530
Max Act: 4.3655. Min Act: -0.1700
Data Index: 3504336 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19