Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3201 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1033. Min Range: -6.1033
Max Act: 6.1033. Min Act: -0.1700
Data Index: 4351959 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1033. Min Range: -6.1033
Max Act: 5.7283. Min Act: -0.1700
Data Index: 4822800 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1033. Min Range: -6.1033
Max Act: 5.7283. Min Act: -0.1700
Data Index: 8764298 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1033. Min Range: -6.1033
Max Act: 5.5408. Min Act: -0.1700
Data Index: 3604634 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1033. Min Range: -6.1033
Max Act: 5.5408. Min Act: -0.1700
Data Index: 5058487 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1033. Min Range: -6.1033
Max Act: 5.5408. Min Act: -0.1700
Data Index: 781679 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1033. Min Range: -6.1033
Max Act: 5.5408. Min Act: -0.1700
Data Index: 7544556 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1033. Min Range: -6.1033
Max Act: 5.4783. Min Act: -0.1700
Data Index: 2021900 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1033. Min Range: -6.1033
Max Act: 5.4783. Min Act: -0.1700
Data Index: 1859646 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1033. Min Range: -6.1033
Max Act: 5.4783. Min Act: -0.1700
Data Index: 2491549 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1033. Min Range: -6.1033
Max Act: 5.4471. Min Act: -0.1700
Data Index: 1499460 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1033. Min Range: -6.1033
Max Act: 5.4471. Min Act: -0.1700
Data Index: 616613 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1033. Min Range: -6.1033
Max Act: 5.4471. Min Act: -0.1700
Data Index: 977465 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1033. Min Range: -6.1033
Max Act: 5.4471. Min Act: -0.1700
Data Index: 78922 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1033. Min Range: -6.1033
Max Act: 5.4471. Min Act: -0.1700
Data Index: 11985 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1033. Min Range: -6.1033
Max Act: 5.4158. Min Act: -0.1700
Data Index: 3175450 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1033. Min Range: -6.1033
Max Act: 5.4158. Min Act: -0.1700
Data Index: 4776920 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1033. Min Range: -6.1033
Max Act: 5.4471. Min Act: -0.1700
Data Index: 6133040 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1033. Min Range: -6.1033
Max Act: 5.3846. Min Act: -0.1700
Data Index: 8587334 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1033. Min Range: -6.1033
Max Act: 5.3846. Min Act: -0.1700
Data Index: 3068282 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19