Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4790 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5482. Min Range: -7.5482
Max Act: 7.5482. Min Act: -0.1700
Data Index: 810670 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5482. Min Range: -7.5482
Max Act: 7.4232. Min Act: -0.1700
Data Index: 5969012 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5482. Min Range: -7.5482
Max Act: 7.3295. Min Act: -0.1700
Data Index: 2931701 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5482. Min Range: -7.5482
Max Act: 6.8920. Min Act: -0.1700
Data Index: 7008297 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5482. Min Range: -7.5482
Max Act: 6.7982. Min Act: -0.1700
Data Index: 3779757 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5482. Min Range: -7.5482
Max Act: 6.7982. Min Act: -0.1700
Data Index: 7524050 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5482. Min Range: -7.5482
Max Act: 6.6420. Min Act: -0.1700
Data Index: 7837517 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5482. Min Range: -7.5482
Max Act: 6.6420. Min Act: -0.1700
Data Index: 350285 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5482. Min Range: -7.5482
Max Act: 6.6107. Min Act: -0.1700
Data Index: 1339903 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5482. Min Range: -7.5482
Max Act: 6.6107. Min Act: -0.1700
Data Index: 8692497 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5482. Min Range: -7.5482
Max Act: 6.5482. Min Act: -0.1700
Data Index: 8644185 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5482. Min Range: -7.5482
Max Act: 6.5795. Min Act: -0.1700
Data Index: 6693324 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5482. Min Range: -7.5482
Max Act: 6.5482. Min Act: -0.1700
Data Index: 1547737 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5482. Min Range: -7.5482
Max Act: 6.5795. Min Act: -0.1700
Data Index: 2208991 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5482. Min Range: -7.5482
Max Act: 6.5170. Min Act: -0.1700
Data Index: 6413980 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5482. Min Range: -7.5482
Max Act: 6.5170. Min Act: -0.1700
Data Index: 1213320 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5482. Min Range: -7.5482
Max Act: 6.5482. Min Act: -0.1700
Data Index: 7068908 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5482. Min Range: -7.5482
Max Act: 6.5170. Min Act: -0.1700
Data Index: 6315829 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5482. Min Range: -7.5482
Max Act: 6.5170. Min Act: -0.1700
Data Index: 6326180 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5482. Min Range: -7.5482
Max Act: 6.4857. Min Act: -0.1700
Data Index: 4006246 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19