Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 863 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1777. Min Range: -3.1777
Max Act: 3.1777. Min Act: -0.1700
Data Index: 4285892 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1777. Min Range: -3.1777
Max Act: 3.1462. Min Act: -0.1700
Data Index: 4218715 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1777. Min Range: -3.1777
Max Act: 3.1462. Min Act: -0.1700
Data Index: 7092638 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1777. Min Range: -3.1777
Max Act: 3.1147. Min Act: -0.1700
Data Index: 8102606 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1777. Min Range: -3.1777
Max Act: 3.1305. Min Act: -0.1700
Data Index: 6422757 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1777. Min Range: -3.1777
Max Act: 3.1147. Min Act: -0.1700
Data Index: 5239337 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1777. Min Range: -3.1777
Max Act: 3.0990. Min Act: -0.1700
Data Index: 1966868 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1777. Min Range: -3.1777
Max Act: 3.1305. Min Act: -0.1700
Data Index: 2005856 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1777. Min Range: -3.1777
Max Act: 3.0990. Min Act: -0.1700
Data Index: 7228706 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1777. Min Range: -3.1777
Max Act: 3.0990. Min Act: -0.1700
Data Index: 2496095 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1777. Min Range: -3.1777
Max Act: 3.0832. Min Act: -0.1700
Data Index: 1281500 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1777. Min Range: -3.1777
Max Act: 3.1147. Min Act: -0.1700
Data Index: 2693051 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1777. Min Range: -3.1777
Max Act: 3.1147. Min Act: -0.1700
Data Index: 4305089 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1777. Min Range: -3.1777
Max Act: 3.0832. Min Act: -0.1700
Data Index: 6425325 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1777. Min Range: -3.1777
Max Act: 3.0832. Min Act: -0.1700
Data Index: 3326947 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1777. Min Range: -3.1777
Max Act: 3.0832. Min Act: -0.1700
Data Index: 3136126 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1777. Min Range: -3.1777
Max Act: 3.0675. Min Act: -0.1700
Data Index: 669255 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1777. Min Range: -3.1777
Max Act: 3.0675. Min Act: -0.1700
Data Index: 4265703 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1777. Min Range: -3.1777
Max Act: 3.0675. Min Act: -0.1700
Data Index: 2821918 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1777. Min Range: -3.1777
Max Act: 3.0675. Min Act: -0.1700
Data Index: 2884197 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19