Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3071 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6204. Min Range: -5.6204
Max Act: 5.6204. Min Act: -0.1700
Data Index: 7936881 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6204. Min Range: -5.6204
Max Act: 5.6204. Min Act: -0.1700
Data Index: 7664272 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6204. Min Range: -5.6204
Max Act: 5.6204. Min Act: -0.1700
Data Index: 2640471 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6204. Min Range: -5.6204
Max Act: 5.6204. Min Act: -0.1700
Data Index: 7436733 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6204. Min Range: -5.6204
Max Act: 5.5891. Min Act: -0.1700
Data Index: 8667961 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6204. Min Range: -5.6204
Max Act: 5.5891. Min Act: -0.1700
Data Index: 2993673 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6204. Min Range: -5.6204
Max Act: 5.5579. Min Act: -0.1700
Data Index: 5034421 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6204. Min Range: -5.6204
Max Act: 5.5579. Min Act: -0.1700
Data Index: 1589671 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6204. Min Range: -5.6204
Max Act: 5.5266. Min Act: -0.1700
Data Index: 373990 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6204. Min Range: -5.6204
Max Act: 5.5266. Min Act: -0.1700
Data Index: 675838 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6204. Min Range: -5.6204
Max Act: 5.5266. Min Act: -0.1700
Data Index: 7664269 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6204. Min Range: -5.6204
Max Act: 5.4954. Min Act: -0.1700
Data Index: 4037392 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6204. Min Range: -5.6204
Max Act: 5.4954. Min Act: -0.1700
Data Index: 395712 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6204. Min Range: -5.6204
Max Act: 5.4954. Min Act: -0.1700
Data Index: 4145806 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6204. Min Range: -5.6204
Max Act: 5.5266. Min Act: -0.1700
Data Index: 1088442 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6204. Min Range: -5.6204
Max Act: 5.4954. Min Act: -0.1700
Data Index: 7154936 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6204. Min Range: -5.6204
Max Act: 5.4954. Min Act: -0.1700
Data Index: 5938424 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6204. Min Range: -5.6204
Max Act: 5.4954. Min Act: -0.1700
Data Index: 1531470 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6204. Min Range: -5.6204
Max Act: 5.4641. Min Act: -0.1700
Data Index: 7705291 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6204. Min Range: -5.6204
Max Act: 5.5266. Min Act: -0.1700
Data Index: 2235139 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19