Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2680 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.4257. Min Act: -0.1700
Data Index: 6975556 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.4100. Min Act: -0.1700
Data Index: 6689815 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.3943. Min Act: -0.1700
Data Index: 2854665 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.3943. Min Act: -0.1700
Data Index: 2751673 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.3630. Min Act: -0.1700
Data Index: 2842064 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.3630. Min Act: -0.1700
Data Index: 3747328 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.3473. Min Act: -0.1700
Data Index: 1568430 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.3473. Min Act: -0.1700
Data Index: 7798877 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.3316. Min Act: -0.1700
Data Index: 5923016 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.3316. Min Act: -0.1700
Data Index: 2011989 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.3316. Min Act: -0.1700
Data Index: 3706909 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.3316. Min Act: -0.1700
Data Index: 3432558 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.3316. Min Act: -0.1700
Data Index: 4273477 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.3159. Min Act: -0.1700
Data Index: 6889930 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.3159. Min Act: -0.1700
Data Index: 3155360 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.3159. Min Act: -0.1700
Data Index: 7102535 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.3159. Min Act: -0.1700
Data Index: 1507296 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.3159. Min Act: -0.1700
Data Index: 1692954 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.3159. Min Act: -0.1700
Data Index: 6221007 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.3159. Min Act: -0.1700
Data Index: 2241358 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19