Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4297 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4651. Min Range: -6.4651
Max Act: 6.4651. Min Act: -0.1700
Data Index: 3958970 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4651. Min Range: -6.4651
Max Act: 6.4026. Min Act: -0.1700
Data Index: 2345445 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4651. Min Range: -6.4651
Max Act: 6.3713. Min Act: -0.1700
Data Index: 3217315 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4651. Min Range: -6.4651
Max Act: 6.0901. Min Act: -0.1700
Data Index: 8091322 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4651. Min Range: -6.4651
Max Act: 6.1213. Min Act: -0.1700
Data Index: 537597 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4651. Min Range: -6.4651
Max Act: 6.1213. Min Act: -0.1700
Data Index: 7717510 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4651. Min Range: -6.4651
Max Act: 6.0901. Min Act: -0.1700
Data Index: 6877035 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4651. Min Range: -6.4651
Max Act: 6.0901. Min Act: -0.1700
Data Index: 7929691 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4651. Min Range: -6.4651
Max Act: 6.0901. Min Act: -0.1700
Data Index: 7867601 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4651. Min Range: -6.4651
Max Act: 6.0901. Min Act: -0.1700
Data Index: 6262344 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4651. Min Range: -6.4651
Max Act: 6.0901. Min Act: -0.1700
Data Index: 8812119 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4651. Min Range: -6.4651
Max Act: 6.0588. Min Act: -0.1700
Data Index: 7071589 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4651. Min Range: -6.4651
Max Act: 6.0588. Min Act: -0.1700
Data Index: 6421544 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4651. Min Range: -6.4651
Max Act: 6.0588. Min Act: -0.1700
Data Index: 2853422 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4651. Min Range: -6.4651
Max Act: 6.0276. Min Act: -0.1700
Data Index: 3051252 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4651. Min Range: -6.4651
Max Act: 6.0276. Min Act: -0.1700
Data Index: 5989942 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4651. Min Range: -6.4651
Max Act: 5.9963. Min Act: -0.1700
Data Index: 5764842 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4651. Min Range: -6.4651
Max Act: 5.9651. Min Act: -0.1700
Data Index: 4637042 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4651. Min Range: -6.4651
Max Act: 5.9651. Min Act: -0.1700
Data Index: 4851091 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4651. Min Range: -6.4651
Max Act: 5.9651. Min Act: -0.1700
Data Index: 2609754 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19