Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1412 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7768. Min Range: -4.7768
Max Act: 4.7768. Min Act: -0.1700
Data Index: 1804027 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7768. Min Range: -4.7768
Max Act: 4.4643. Min Act: -0.1700
Data Index: 6416157 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7768. Min Range: -4.7768
Max Act: 4.4018. Min Act: -0.1700
Data Index: 4476844 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7768. Min Range: -4.7768
Max Act: 4.4018. Min Act: -0.1700
Data Index: 5137522 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7768. Min Range: -4.7768
Max Act: 4.3080. Min Act: -0.1700
Data Index: 6179526 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7768. Min Range: -4.7768
Max Act: 4.2455. Min Act: -0.1700
Data Index: 6369946 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7768. Min Range: -4.7768
Max Act: 4.2768. Min Act: -0.1700
Data Index: 7541617 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7768. Min Range: -4.7768
Max Act: 4.2455. Min Act: -0.1700
Data Index: 517610 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7768. Min Range: -4.7768
Max Act: 4.2143. Min Act: -0.1700
Data Index: 6564761 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7768. Min Range: -4.7768
Max Act: 4.2455. Min Act: -0.1700
Data Index: 8434063 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7768. Min Range: -4.7768
Max Act: 4.2143. Min Act: -0.1700
Data Index: 8411662 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7768. Min Range: -4.7768
Max Act: 4.2143. Min Act: -0.1700
Data Index: 2004218 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7768. Min Range: -4.7768
Max Act: 4.2143. Min Act: -0.1700
Data Index: 7525143 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7768. Min Range: -4.7768
Max Act: 4.2455. Min Act: -0.1700
Data Index: 5061272 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7768. Min Range: -4.7768
Max Act: 4.2143. Min Act: -0.1700
Data Index: 1804967 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7768. Min Range: -4.7768
Max Act: 4.1830. Min Act: -0.1700
Data Index: 897736 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7768. Min Range: -4.7768
Max Act: 4.1830. Min Act: -0.1700
Data Index: 3153824 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7768. Min Range: -4.7768
Max Act: 4.1830. Min Act: -0.1700
Data Index: 1372758 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7768. Min Range: -4.7768
Max Act: 4.1830. Min Act: -0.1700
Data Index: 3549332 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7768. Min Range: -4.7768
Max Act: 4.1830. Min Act: -0.1700
Data Index: 3888818 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19