Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3372 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.6469. Min Act: -0.1700
Data Index: 3200782 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.6469. Min Act: -0.1700
Data Index: 8299899 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.6156. Min Act: -0.1700
Data Index: 5328804 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.6156. Min Act: -0.1700
Data Index: 4410335 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.6156. Min Act: -0.1700
Data Index: 3070641 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.4906. Min Act: -0.1700
Data Index: 184857 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.4594. Min Act: -0.1700
Data Index: 614650 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.4594. Min Act: -0.1700
Data Index: 1340564 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.4281. Min Act: -0.1700
Data Index: 3740955 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.4281. Min Act: -0.1700
Data Index: 2926045 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.4281. Min Act: -0.1700
Data Index: 5707368 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.3969. Min Act: -0.1700
Data Index: 5379026 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.3969. Min Act: -0.1700
Data Index: 4169219 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.3969. Min Act: -0.1700
Data Index: 6356016 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.3656. Min Act: -0.1700
Data Index: 2875104 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.3656. Min Act: -0.1700
Data Index: 3980080 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.3656. Min Act: -0.1700
Data Index: 3047421 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.3656. Min Act: -0.1700
Data Index: 2503422 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.3344. Min Act: -0.1700
Data Index: 1444413 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6469. Min Range: -5.6469
Max Act: 5.3656. Min Act: -0.1700
Data Index: 1340565 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19