Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3632 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3016. Min Range: -2.3016
Max Act: 2.3016. Min Act: -0.1699
Data Index: 3951431 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3016. Min Range: -2.3016
Max Act: 2.2356. Min Act: -0.1700
Data Index: 4649964 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3016. Min Range: -2.3016
Max Act: 2.2190. Min Act: -0.1700
Data Index: 2866188 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3016. Min Range: -2.3016
Max Act: 2.2025. Min Act: -0.1700
Data Index: 3311139 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3016. Min Range: -2.3016
Max Act: 2.1692. Min Act: -0.1700
Data Index: 5287378 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3016. Min Range: -2.3016
Max Act: 2.1526. Min Act: -0.1700
Data Index: 4437510 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3016. Min Range: -2.3016
Max Act: 2.1526. Min Act: -0.1700
Data Index: 5823558 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3016. Min Range: -2.3016
Max Act: 2.1359. Min Act: -0.1700
Data Index: 7405760 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3016. Min Range: -2.3016
Max Act: 2.1192. Min Act: -0.1700
Data Index: 3350801 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3016. Min Range: -2.3016
Max Act: 2.1192. Min Act: -0.1700
Data Index: 6988480 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3016. Min Range: -2.3016
Max Act: 2.1192. Min Act: -0.1700
Data Index: 628645 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3016. Min Range: -2.3016
Max Act: 2.1025. Min Act: -0.1700
Data Index: 5823556 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3016. Min Range: -2.3016
Max Act: 2.0857. Min Act: -0.1700
Data Index: 394270 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3016. Min Range: -2.3016
Max Act: 2.0857. Min Act: -0.1700
Data Index: 6087613 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3016. Min Range: -2.3016
Max Act: 2.0857. Min Act: -0.1700
Data Index: 3861252 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3016. Min Range: -2.3016
Max Act: 2.0857. Min Act: -0.1700
Data Index: 343644 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3016. Min Range: -2.3016
Max Act: 2.0857. Min Act: -0.1700
Data Index: 1789387 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3016. Min Range: -2.3016
Max Act: 2.0857. Min Act: -0.1700
Data Index: 199039 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3016. Min Range: -2.3016
Max Act: 2.0857. Min Act: -0.1700
Data Index: 6940451 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3016. Min Range: -2.3016
Max Act: 2.0689. Min Act: -0.1700
Data Index: 6164518 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19