Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2742 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7039. Min Range: -3.7039
Max Act: 3.7039. Min Act: -0.1700
Data Index: 6667795 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7039. Min Range: -3.7039
Max Act: 3.6100. Min Act: -0.1700
Data Index: 4532987 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7039. Min Range: -3.7039
Max Act: 3.5787. Min Act: -0.1700
Data Index: 8526958 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7039. Min Range: -3.7039
Max Act: 3.5474. Min Act: -0.1700
Data Index: 1028518 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7039. Min Range: -3.7039
Max Act: 3.5317. Min Act: -0.1700
Data Index: 8108011 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7039. Min Range: -3.7039
Max Act: 3.5317. Min Act: -0.1700
Data Index: 6241071 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7039. Min Range: -3.7039
Max Act: 3.5161. Min Act: -0.1700
Data Index: 4511149 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7039. Min Range: -3.7039
Max Act: 3.4847. Min Act: -0.1700
Data Index: 4188153 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7039. Min Range: -3.7039
Max Act: 3.5161. Min Act: -0.1700
Data Index: 3421576 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7039. Min Range: -3.7039
Max Act: 3.4847. Min Act: -0.1700
Data Index: 8526959 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7039. Min Range: -3.7039
Max Act: 3.4847. Min Act: -0.1700
Data Index: 6680524 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7039. Min Range: -3.7039
Max Act: 3.4377. Min Act: -0.1700
Data Index: 2453175 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7039. Min Range: -3.7039
Max Act: 3.4221. Min Act: -0.1700
Data Index: 5473232 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7039. Min Range: -3.7039
Max Act: 3.4221. Min Act: -0.1700
Data Index: 3396641 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7039. Min Range: -3.7039
Max Act: 3.3907. Min Act: -0.1700
Data Index: 8595203 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7039. Min Range: -3.7039
Max Act: 3.3907. Min Act: -0.1700
Data Index: 6974802 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7039. Min Range: -3.7039
Max Act: 3.3750. Min Act: -0.1700
Data Index: 7186780 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7039. Min Range: -3.7039
Max Act: 3.3750. Min Act: -0.1700
Data Index: 1445778 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7039. Min Range: -3.7039
Max Act: 3.3280. Min Act: -0.1700
Data Index: 4410076 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7039. Min Range: -3.7039
Max Act: 3.3123. Min Act: -0.1700
Data Index: 6973587 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19