Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2443 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3048. Min Range: -4.3048
Max Act: 4.3048. Min Act: -0.1700
Data Index: 5574006 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3048. Min Range: -4.3048
Max Act: 4.3048. Min Act: -0.1700
Data Index: 7491830 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3048. Min Range: -4.3048
Max Act: 4.2735. Min Act: -0.1700
Data Index: 5453537 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3048. Min Range: -4.3048
Max Act: 4.2735. Min Act: -0.1700
Data Index: 6546711 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3048. Min Range: -4.3048
Max Act: 4.2735. Min Act: -0.1700
Data Index: 8037216 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3048. Min Range: -4.3048
Max Act: 4.2110. Min Act: -0.1700
Data Index: 8130975 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3048. Min Range: -4.3048
Max Act: 4.2423. Min Act: -0.1700
Data Index: 327098 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3048. Min Range: -4.3048
Max Act: 4.1798. Min Act: -0.1700
Data Index: 5167700 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3048. Min Range: -4.3048
Max Act: 4.2110. Min Act: -0.1700
Data Index: 1417905 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3048. Min Range: -4.3048
Max Act: 4.1798. Min Act: -0.1700
Data Index: 6105231 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3048. Min Range: -4.3048
Max Act: 4.1798. Min Act: -0.1700
Data Index: 4019877 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3048. Min Range: -4.3048
Max Act: 4.1798. Min Act: -0.1700
Data Index: 5255504 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3048. Min Range: -4.3048
Max Act: 4.1798. Min Act: -0.1700
Data Index: 8452270 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3048. Min Range: -4.3048
Max Act: 4.1172. Min Act: -0.1700
Data Index: 3232640 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3048. Min Range: -4.3048
Max Act: 4.1172. Min Act: -0.1700
Data Index: 7204438 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3048. Min Range: -4.3048
Max Act: 4.1172. Min Act: -0.1700
Data Index: 814221 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3048. Min Range: -4.3048
Max Act: 4.1172. Min Act: -0.1700
Data Index: 266846 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3048. Min Range: -4.3048
Max Act: 4.0860. Min Act: -0.1700
Data Index: 4038669 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3048. Min Range: -4.3048
Max Act: 4.0860. Min Act: -0.1700
Data Index: 8642360 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3048. Min Range: -4.3048
Max Act: 4.0860. Min Act: -0.1700
Data Index: 83689 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19