Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3733 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9098. Min Range: -2.9098
Max Act: 2.9098. Min Act: -0.1700
Data Index: 2903163 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9098. Min Range: -2.9098
Max Act: 2.9098. Min Act: -0.1700
Data Index: 3792099 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9098. Min Range: -2.9098
Max Act: 2.8781. Min Act: -0.1700
Data Index: 4431466 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9098. Min Range: -2.9098
Max Act: 2.8622. Min Act: -0.1700
Data Index: 5106981 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9098. Min Range: -2.9098
Max Act: 2.8304. Min Act: -0.1700
Data Index: 7396477 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9098. Min Range: -2.9098
Max Act: 2.7986. Min Act: -0.1700
Data Index: 2793135 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9098. Min Range: -2.9098
Max Act: 2.7827. Min Act: -0.1700
Data Index: 5666595 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9098. Min Range: -2.9098
Max Act: 2.7827. Min Act: -0.1700
Data Index: 3950111 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9098. Min Range: -2.9098
Max Act: 2.7667. Min Act: -0.1700
Data Index: 7860820 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9098. Min Range: -2.9098
Max Act: 2.7508. Min Act: -0.1700
Data Index: 2494926 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9098. Min Range: -2.9098
Max Act: 2.7348. Min Act: -0.1700
Data Index: 3672605 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9098. Min Range: -2.9098
Max Act: 2.7348. Min Act: -0.1700
Data Index: 5693487 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9098. Min Range: -2.9098
Max Act: 2.7188. Min Act: -0.1700
Data Index: 7406756 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9098. Min Range: -2.9098
Max Act: 2.7348. Min Act: -0.1700
Data Index: 5245231 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9098. Min Range: -2.9098
Max Act: 2.7028. Min Act: -0.1700
Data Index: 501606 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9098. Min Range: -2.9098
Max Act: 2.7028. Min Act: -0.1700
Data Index: 4867230 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9098. Min Range: -2.9098
Max Act: 2.7188. Min Act: -0.1700
Data Index: 6741401 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9098. Min Range: -2.9098
Max Act: 2.7188. Min Act: -0.1700
Data Index: 7616081 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9098. Min Range: -2.9098
Max Act: 2.7028. Min Act: -0.1700
Data Index: 6425539 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9098. Min Range: -2.9098
Max Act: 2.7028. Min Act: -0.1700
Data Index: 5169654 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19