Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1791 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6238. Min Range: -6.6238
Max Act: 6.6238. Min Act: -0.1700
Data Index: 5210844 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6238. Min Range: -6.6238
Max Act: 6.4363. Min Act: -0.1700
Data Index: 7368271 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6238. Min Range: -6.6238
Max Act: 6.3738. Min Act: -0.1700
Data Index: 2941468 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6238. Min Range: -6.6238
Max Act: 6.3113. Min Act: -0.1700
Data Index: 2520706 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6238. Min Range: -6.6238
Max Act: 6.3113. Min Act: -0.1700
Data Index: 3619241 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6238. Min Range: -6.6238
Max Act: 6.3113. Min Act: -0.1700
Data Index: 5475819 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6238. Min Range: -6.6238
Max Act: 6.3113. Min Act: -0.1700
Data Index: 2363913 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6238. Min Range: -6.6238
Max Act: 6.3425. Min Act: -0.1700
Data Index: 6276990 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6238. Min Range: -6.6238
Max Act: 6.2800. Min Act: -0.1700
Data Index: 5349140 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6238. Min Range: -6.6238
Max Act: 6.2488. Min Act: -0.1700
Data Index: 3922774 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6238. Min Range: -6.6238
Max Act: 6.2488. Min Act: -0.1700
Data Index: 1194330 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6238. Min Range: -6.6238
Max Act: 6.2488. Min Act: -0.1700
Data Index: 7251602 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6238. Min Range: -6.6238
Max Act: 6.2488. Min Act: -0.1700
Data Index: 5746265 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6238. Min Range: -6.6238
Max Act: 6.2488. Min Act: -0.1700
Data Index: 4601001 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6238. Min Range: -6.6238
Max Act: 6.1863. Min Act: -0.1700
Data Index: 5740022 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6238. Min Range: -6.6238
Max Act: 6.2175. Min Act: -0.1700
Data Index: 1181090 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6238. Min Range: -6.6238
Max Act: 6.1863. Min Act: -0.1700
Data Index: 4303058 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6238. Min Range: -6.6238
Max Act: 6.2175. Min Act: -0.1700
Data Index: 7684723 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6238. Min Range: -6.6238
Max Act: 6.1863. Min Act: -0.1700
Data Index: 1279192 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6238. Min Range: -6.6238
Max Act: 6.1863. Min Act: -0.1700
Data Index: 3627516 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19