Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 256 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4005. Min Range: -7.4005
Max Act: 7.4005. Min Act: -0.1700
Data Index: 3710080 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4005. Min Range: -7.4005
Max Act: 7.2442. Min Act: -0.1700
Data Index: 4543756 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4005. Min Range: -7.4005
Max Act: 7.1505. Min Act: -0.1700
Data Index: 493937 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4005. Min Range: -7.4005
Max Act: 7.1192. Min Act: -0.1700
Data Index: 5534660 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4005. Min Range: -7.4005
Max Act: 7.0255. Min Act: -0.1700
Data Index: 7420320 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4005. Min Range: -7.4005
Max Act: 6.9942. Min Act: -0.1700
Data Index: 6226202 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4005. Min Range: -7.4005
Max Act: 6.9317. Min Act: -0.1700
Data Index: 3094030 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4005. Min Range: -7.4005
Max Act: 6.9317. Min Act: -0.1700
Data Index: 5654165 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4005. Min Range: -7.4005
Max Act: 6.9630. Min Act: -0.1700
Data Index: 7111287 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4005. Min Range: -7.4005
Max Act: 6.9630. Min Act: -0.1700
Data Index: 4568088 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4005. Min Range: -7.4005
Max Act: 6.9317. Min Act: -0.1700
Data Index: 5750284 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4005. Min Range: -7.4005
Max Act: 6.9630. Min Act: -0.1700
Data Index: 8764423 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4005. Min Range: -7.4005
Max Act: 6.9005. Min Act: -0.1700
Data Index: 6790120 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4005. Min Range: -7.4005
Max Act: 6.8692. Min Act: -0.1700
Data Index: 7424555 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4005. Min Range: -7.4005
Max Act: 6.8692. Min Act: -0.1700
Data Index: 1019167 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4005. Min Range: -7.4005
Max Act: 6.8692. Min Act: -0.1700
Data Index: 382078 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4005. Min Range: -7.4005
Max Act: 6.8380. Min Act: -0.1700
Data Index: 4351780 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4005. Min Range: -7.4005
Max Act: 6.8067. Min Act: -0.1700
Data Index: 8091594 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4005. Min Range: -7.4005
Max Act: 6.8067. Min Act: -0.1700
Data Index: 137145 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4005. Min Range: -7.4005
Max Act: 6.8067. Min Act: -0.1700
Data Index: 653165 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19