Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1799 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0431. Min Range: -7.0431
Max Act: 7.0431. Min Act: -0.1700
Data Index: 8394554 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0431. Min Range: -7.0431
Max Act: 6.8869. Min Act: -0.1700
Data Index: 8748994 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0431. Min Range: -7.0431
Max Act: 6.7306. Min Act: -0.1700
Data Index: 8826567 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0431. Min Range: -7.0431
Max Act: 6.7306. Min Act: -0.1700
Data Index: 4197256 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0431. Min Range: -7.0431
Max Act: 6.7306. Min Act: -0.1700
Data Index: 4944838 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0431. Min Range: -7.0431
Max Act: 6.7306. Min Act: -0.1700
Data Index: 4011552 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0431. Min Range: -7.0431
Max Act: 6.6994. Min Act: -0.1700
Data Index: 1628333 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0431. Min Range: -7.0431
Max Act: 6.6681. Min Act: -0.1700
Data Index: 703027 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0431. Min Range: -7.0431
Max Act: 6.6369. Min Act: -0.1700
Data Index: 6443133 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0431. Min Range: -7.0431
Max Act: 6.6056. Min Act: -0.1700
Data Index: 2029521 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0431. Min Range: -7.0431
Max Act: 6.6056. Min Act: -0.1700
Data Index: 4567164 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0431. Min Range: -7.0431
Max Act: 6.5744. Min Act: -0.1700
Data Index: 363153 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0431. Min Range: -7.0431
Max Act: 6.5744. Min Act: -0.1700
Data Index: 5768144 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0431. Min Range: -7.0431
Max Act: 6.5744. Min Act: -0.1700
Data Index: 3147239 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0431. Min Range: -7.0431
Max Act: 6.5744. Min Act: -0.1700
Data Index: 1034596 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0431. Min Range: -7.0431
Max Act: 6.5431. Min Act: -0.1700
Data Index: 1427498 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0431. Min Range: -7.0431
Max Act: 6.5431. Min Act: -0.1700
Data Index: 2730422 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0431. Min Range: -7.0431
Max Act: 6.5431. Min Act: -0.1700
Data Index: 2954367 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0431. Min Range: -7.0431
Max Act: 6.5119. Min Act: -0.1700
Data Index: 4350221 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0431. Min Range: -7.0431
Max Act: 6.5119. Min Act: -0.1700
Data Index: 1006901 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19