Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1228 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6422. Min Range: -10.6422
Max Act: 10.6422. Min Act: -0.1700
Data Index: 768463 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6422. Min Range: -10.6422
Max Act: 10.2672. Min Act: -0.1700
Data Index: 5882336 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6422. Min Range: -10.6422
Max Act: 10.1422. Min Act: -0.1700
Data Index: 53786 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6422. Min Range: -10.6422
Max Act: 10.0797. Min Act: -0.1700
Data Index: 4478384 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6422. Min Range: -10.6422
Max Act: 9.9547. Min Act: -0.1700
Data Index: 4542266 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6422. Min Range: -10.6422
Max Act: 9.9547. Min Act: -0.1700
Data Index: 2437745 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6422. Min Range: -10.6422
Max Act: 9.8297. Min Act: -0.1700
Data Index: 5744621 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6422. Min Range: -10.6422
Max Act: 9.8922. Min Act: -0.1700
Data Index: 685840 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6422. Min Range: -10.6422
Max Act: 9.8922. Min Act: -0.1700
Data Index: 7695394 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6422. Min Range: -10.6422
Max Act: 9.8297. Min Act: -0.1700
Data Index: 1061809 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6422. Min Range: -10.6422
Max Act: 9.6422. Min Act: -0.1700
Data Index: 5618429 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6422. Min Range: -10.6422
Max Act: 9.7047. Min Act: -0.1700
Data Index: 4352758 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6422. Min Range: -10.6422
Max Act: 9.7047. Min Act: -0.1700
Data Index: 4806478 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6422. Min Range: -10.6422
Max Act: 9.7047. Min Act: -0.1700
Data Index: 3570802 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6422. Min Range: -10.6422
Max Act: 9.7047. Min Act: -0.1700
Data Index: 7677378 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6422. Min Range: -10.6422
Max Act: 9.6422. Min Act: -0.1700
Data Index: 8473624 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6422. Min Range: -10.6422
Max Act: 9.6422. Min Act: -0.1700
Data Index: 5593421 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6422. Min Range: -10.6422
Max Act: 9.6422. Min Act: -0.1700
Data Index: 2004322 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6422. Min Range: -10.6422
Max Act: 9.6422. Min Act: -0.1700
Data Index: 5200055 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6422. Min Range: -10.6422
Max Act: 9.6422. Min Act: -0.1700
Data Index: 3069630 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19