Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6236 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2748. Min Range: -7.2748
Max Act: 7.2748. Min Act: -0.1700
Data Index: 2892084 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2748. Min Range: -7.2748
Max Act: 7.2123. Min Act: -0.1700
Data Index: 3492214 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2748. Min Range: -7.2748
Max Act: 7.2123. Min Act: -0.1700
Data Index: 6422990 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2748. Min Range: -7.2748
Max Act: 7.2123. Min Act: -0.1700
Data Index: 6392479 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2748. Min Range: -7.2748
Max Act: 7.2123. Min Act: -0.1700
Data Index: 874225 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2748. Min Range: -7.2748
Max Act: 7.2123. Min Act: -0.1700
Data Index: 4480106 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2748. Min Range: -7.2748
Max Act: 7.2123. Min Act: -0.1700
Data Index: 511392 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2748. Min Range: -7.2748
Max Act: 7.1498. Min Act: -0.1700
Data Index: 5424309 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2748. Min Range: -7.2748
Max Act: 7.1498. Min Act: -0.1700
Data Index: 694843 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2748. Min Range: -7.2748
Max Act: 7.1498. Min Act: -0.1700
Data Index: 5320544 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2748. Min Range: -7.2748
Max Act: 7.1498. Min Act: -0.1700
Data Index: 1688209 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2748. Min Range: -7.2748
Max Act: 7.1498. Min Act: -0.1700
Data Index: 5048689 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2748. Min Range: -7.2748
Max Act: 7.1498. Min Act: -0.1700
Data Index: 2128794 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2748. Min Range: -7.2748
Max Act: 7.1498. Min Act: -0.1700
Data Index: 1622468 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2748. Min Range: -7.2748
Max Act: 7.1498. Min Act: -0.1700
Data Index: 2708729 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2748. Min Range: -7.2748
Max Act: 7.1498. Min Act: -0.1700
Data Index: 167134 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2748. Min Range: -7.2748
Max Act: 7.1498. Min Act: -0.1700
Data Index: 2023726 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2748. Min Range: -7.2748
Max Act: 7.1498. Min Act: -0.1700
Data Index: 4188337 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2748. Min Range: -7.2748
Max Act: 7.2123. Min Act: -0.1700
Data Index: 1726514 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2748. Min Range: -7.2748
Max Act: 7.1498. Min Act: -0.1700
Data Index: 3813785 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19