Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1564 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.5005. Min Act: -0.1700
Data Index: 5977603 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.3130. Min Act: -0.1700
Data Index: 8328688 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.2817. Min Act: -0.1700
Data Index: 5985767 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.2192. Min Act: -0.1700
Data Index: 1779922 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.1880. Min Act: -0.1700
Data Index: 1662376 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.1255. Min Act: -0.1700
Data Index: 1999103 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.1567. Min Act: -0.1700
Data Index: 8102875 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.1567. Min Act: -0.1700
Data Index: 7300719 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.0942. Min Act: -0.1700
Data Index: 7456498 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.0630. Min Act: -0.1700
Data Index: 604194 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.0630. Min Act: -0.1700
Data Index: 5606228 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.0630. Min Act: -0.1700
Data Index: 8742155 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.0317. Min Act: -0.1700
Data Index: 2357504 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.0317. Min Act: -0.1700
Data Index: 8543045 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.0317. Min Act: -0.1700
Data Index: 8324390 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.0317. Min Act: -0.1700
Data Index: 6571114 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.0317. Min Act: -0.1700
Data Index: 3811388 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.0317. Min Act: -0.1700
Data Index: 5259035 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.0004. Min Act: -0.1700
Data Index: 4703826 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5005. Min Range: -4.5005
Max Act: 4.0004. Min Act: -0.1700
Data Index: 5259034 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19