Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3913 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.8288. Min Act: -0.1700
Data Index: 3127285 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.7663. Min Act: -0.1695
Data Index: 1170891 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.7350. Min Act: -0.1700
Data Index: 4582125 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.7350. Min Act: -0.1700
Data Index: 6766936 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.7350. Min Act: -0.1700
Data Index: 5413491 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.7350. Min Act: -0.1700
Data Index: 3127275 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.7038. Min Act: -0.1700
Data Index: 4067432 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.6725. Min Act: -0.1700
Data Index: 6476904 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.7038. Min Act: -0.1700
Data Index: 3561237 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.6725. Min Act: -0.1700
Data Index: 3036342 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.7038. Min Act: -0.1700
Data Index: 6039875 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.7038. Min Act: -0.1700
Data Index: 230251 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.7038. Min Act: -0.1700
Data Index: 8660974 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.7038. Min Act: -0.1700
Data Index: 4582528 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.6725. Min Act: -0.1700
Data Index: 3275665 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.6413. Min Act: -0.1700
Data Index: 6259645 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.6725. Min Act: -0.1700
Data Index: 1006484 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.6725. Min Act: -0.1700
Data Index: 2934342 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.6725. Min Act: -0.1700
Data Index: 3127297 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8288. Min Range: -4.8288
Max Act: 4.6413. Min Act: -0.1700
Data Index: 6513884 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19