Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2813 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6943. Min Range: -6.6943
Max Act: 6.6943. Min Act: -0.1700
Data Index: 4053541 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6943. Min Range: -6.6943
Max Act: 6.5380. Min Act: -0.1700
Data Index: 2640468 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6943. Min Range: -6.6943
Max Act: 6.5068. Min Act: -0.1700
Data Index: 7023621 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6943. Min Range: -6.6943
Max Act: 6.4130. Min Act: -0.1700
Data Index: 3207708 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6943. Min Range: -6.6943
Max Act: 6.4130. Min Act: -0.1700
Data Index: 226159 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6943. Min Range: -6.6943
Max Act: 6.2568. Min Act: -0.1700
Data Index: 1417962 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6943. Min Range: -6.6943
Max Act: 6.2880. Min Act: -0.1700
Data Index: 1073941 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6943. Min Range: -6.6943
Max Act: 6.2568. Min Act: -0.1700
Data Index: 4161132 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6943. Min Range: -6.6943
Max Act: 6.2568. Min Act: -0.1700
Data Index: 80963 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6943. Min Range: -6.6943
Max Act: 6.1943. Min Act: -0.1700
Data Index: 7175432 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6943. Min Range: -6.6943
Max Act: 6.1943. Min Act: -0.1700
Data Index: 5160980 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6943. Min Range: -6.6943
Max Act: 6.1630. Min Act: -0.1700
Data Index: 5934643 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6943. Min Range: -6.6943
Max Act: 6.1630. Min Act: -0.1700
Data Index: 5934651 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6943. Min Range: -6.6943
Max Act: 6.1630. Min Act: -0.1700
Data Index: 6567284 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6943. Min Range: -6.6943
Max Act: 6.1630. Min Act: -0.1700
Data Index: 6118163 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6943. Min Range: -6.6943
Max Act: 6.1943. Min Act: -0.1700
Data Index: 7581807 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6943. Min Range: -6.6943
Max Act: 6.1318. Min Act: -0.1700
Data Index: 2059416 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6943. Min Range: -6.6943
Max Act: 6.1318. Min Act: -0.1700
Data Index: 3574639 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6943. Min Range: -6.6943
Max Act: 6.1630. Min Act: -0.1700
Data Index: 8211115 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6943. Min Range: -6.6943
Max Act: 6.1318. Min Act: -0.1700
Data Index: 2724422 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19