Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2406 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5304. Min Range: -2.5304
Max Act: 2.5304. Min Act: -0.1700
Data Index: 7129240 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5304. Min Range: -2.5304
Max Act: 2.5142. Min Act: -0.1700
Data Index: 1491968 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5304. Min Range: -2.5304
Max Act: 2.5304. Min Act: -0.1700
Data Index: 6418098 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5304. Min Range: -2.5304
Max Act: 2.4980. Min Act: -0.1700
Data Index: 957103 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5304. Min Range: -2.5304
Max Act: 2.4980. Min Act: -0.1700
Data Index: 7352010 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5304. Min Range: -2.5304
Max Act: 2.4818. Min Act: -0.1700
Data Index: 672268 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5304. Min Range: -2.5304
Max Act: 2.4818. Min Act: -0.1700
Data Index: 5821938 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5304. Min Range: -2.5304
Max Act: 2.4656. Min Act: -0.1700
Data Index: 838312 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5304. Min Range: -2.5304
Max Act: 2.4493. Min Act: -0.1700
Data Index: 1920905 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5304. Min Range: -2.5304
Max Act: 2.4656. Min Act: -0.1700
Data Index: 1820436 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5304. Min Range: -2.5304
Max Act: 2.4656. Min Act: -0.1700
Data Index: 560721 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5304. Min Range: -2.5304
Max Act: 2.4493. Min Act: -0.1700
Data Index: 1836913 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5304. Min Range: -2.5304
Max Act: 2.4331. Min Act: -0.1700
Data Index: 2142464 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5304. Min Range: -2.5304
Max Act: 2.4331. Min Act: -0.1700
Data Index: 2996077 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5304. Min Range: -2.5304
Max Act: 2.4168. Min Act: -0.1700
Data Index: 5893308 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5304. Min Range: -2.5304
Max Act: 2.4331. Min Act: -0.1700
Data Index: 7548045 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5304. Min Range: -2.5304
Max Act: 2.4331. Min Act: -0.1700
Data Index: 4036183 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5304. Min Range: -2.5304
Max Act: 2.4331. Min Act: -0.1700
Data Index: 3240069 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5304. Min Range: -2.5304
Max Act: 2.4331. Min Act: -0.1700
Data Index: 4480236 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5304. Min Range: -2.5304
Max Act: 2.4005. Min Act: -0.1700
Data Index: 3262749 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19