Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 44 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7581. Min Range: -4.7581
Max Act: 4.7581. Min Act: -0.1700
Data Index: 1967728 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7581. Min Range: -4.7581
Max Act: 4.6643. Min Act: -0.1700
Data Index: 428322 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7581. Min Range: -4.7581
Max Act: 4.5706. Min Act: -0.1700
Data Index: 1681214 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7581. Min Range: -4.7581
Max Act: 4.5706. Min Act: -0.1700
Data Index: 97827 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7581. Min Range: -4.7581
Max Act: 4.5393. Min Act: -0.1700
Data Index: 6277700 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7581. Min Range: -4.7581
Max Act: 4.5393. Min Act: -0.1700
Data Index: 3354191 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7581. Min Range: -4.7581
Max Act: 4.5706. Min Act: -0.1700
Data Index: 5044178 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7581. Min Range: -4.7581
Max Act: 4.5393. Min Act: -0.1700
Data Index: 4177112 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7581. Min Range: -4.7581
Max Act: 4.5081. Min Act: -0.1700
Data Index: 6746625 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7581. Min Range: -4.7581
Max Act: 4.4768. Min Act: -0.1700
Data Index: 5306613 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7581. Min Range: -4.7581
Max Act: 4.4768. Min Act: -0.1700
Data Index: 4005215 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7581. Min Range: -4.7581
Max Act: 4.4456. Min Act: -0.1700
Data Index: 4239703 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7581. Min Range: -4.7581
Max Act: 4.4456. Min Act: -0.1700
Data Index: 4003267 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7581. Min Range: -4.7581
Max Act: 4.4456. Min Act: -0.1700
Data Index: 3315923 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7581. Min Range: -4.7581
Max Act: 4.4456. Min Act: -0.1700
Data Index: 8473820 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7581. Min Range: -4.7581
Max Act: 4.4456. Min Act: -0.1700
Data Index: 8031323 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7581. Min Range: -4.7581
Max Act: 4.3831. Min Act: -0.1700
Data Index: 184919 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7581. Min Range: -4.7581
Max Act: 4.4143. Min Act: -0.1700
Data Index: 6746624 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7581. Min Range: -4.7581
Max Act: 4.4143. Min Act: -0.1700
Data Index: 7297287 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7581. Min Range: -4.7581
Max Act: 4.4143. Min Act: -0.1700
Data Index: 7503227 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19