Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2809 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0329. Min Range: -6.0329
Max Act: 6.0329. Min Act: -0.1700
Data Index: 8358135 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0329. Min Range: -6.0329
Max Act: 6.0017. Min Act: -0.1700
Data Index: 2643417 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.9392. Min Act: -0.1700
Data Index: 6224710 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.9392. Min Act: -0.1700
Data Index: 7429738 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.9079. Min Act: -0.1700
Data Index: 8532856 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.8142. Min Act: -0.1700
Data Index: 8265349 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.8454. Min Act: -0.1700
Data Index: 254949 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.7517. Min Act: -0.1700
Data Index: 6514023 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.7204. Min Act: -0.1700
Data Index: 8777830 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.6579. Min Act: -0.1700
Data Index: 8545869 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.6267. Min Act: -0.1700
Data Index: 448072 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.6267. Min Act: -0.1700
Data Index: 4122153 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.5642. Min Act: -0.1700
Data Index: 7767937 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.5642. Min Act: -0.1700
Data Index: 4574293 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.5329. Min Act: -0.1700
Data Index: 3598009 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.5329. Min Act: -0.1700
Data Index: 6026088 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.5329. Min Act: -0.1700
Data Index: 5918551 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.5017. Min Act: -0.1700
Data Index: 1027791 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.5329. Min Act: -0.1700
Data Index: 5520566 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0329. Min Range: -6.0329
Max Act: 5.5017. Min Act: -0.1700
Data Index: 629253 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19