Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4423 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7192. Min Range: -5.7192
Max Act: 5.7192. Min Act: -0.1700
Data Index: 7065421 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7192. Min Range: -5.7192
Max Act: 5.6567. Min Act: -0.1700
Data Index: 5953193 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7192. Min Range: -5.7192
Max Act: 5.6567. Min Act: -0.1700
Data Index: 2645944 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7192. Min Range: -5.7192
Max Act: 5.6254. Min Act: -0.1699
Data Index: 3992891 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7192. Min Range: -5.7192
Max Act: 5.6254. Min Act: -0.1700
Data Index: 857552 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7192. Min Range: -5.7192
Max Act: 5.5942. Min Act: -0.1700
Data Index: 1138069 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7192. Min Range: -5.7192
Max Act: 5.5629. Min Act: -0.1700
Data Index: 6294343 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7192. Min Range: -5.7192
Max Act: 5.5317. Min Act: -0.1699
Data Index: 6651510 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7192. Min Range: -5.7192
Max Act: 5.5004. Min Act: -0.1699
Data Index: 3290243 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7192. Min Range: -5.7192
Max Act: 5.4692. Min Act: -0.1700
Data Index: 1073592 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7192. Min Range: -5.7192
Max Act: 5.4692. Min Act: -0.1700
Data Index: 816493 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7192. Min Range: -5.7192
Max Act: 5.5004. Min Act: -0.1700
Data Index: 5559790 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7192. Min Range: -5.7192
Max Act: 5.4379. Min Act: -0.1679
Data Index: 1704600 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7192. Min Range: -5.7192
Max Act: 5.4379. Min Act: -0.1700
Data Index: 7810209 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7192. Min Range: -5.7192
Max Act: 5.4379. Min Act: -0.1700
Data Index: 4853418 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7192. Min Range: -5.7192
Max Act: 5.4379. Min Act: -0.1700
Data Index: 871041 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7192. Min Range: -5.7192
Max Act: 5.4379. Min Act: -0.1700
Data Index: 1347556 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7192. Min Range: -5.7192
Max Act: 5.4067. Min Act: -0.1700
Data Index: 5623083 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7192. Min Range: -5.7192
Max Act: 5.3754. Min Act: -0.1700
Data Index: 4103450 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7192. Min Range: -5.7192
Max Act: 5.4067. Min Act: -0.1700
Data Index: 3668911 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19