Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4602 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4834. Min Range: -8.4834
Max Act: 8.4834. Min Act: -0.1700
Data Index: 6374716 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4834. Min Range: -8.4834
Max Act: 8.2022. Min Act: -0.1700
Data Index: 4685149 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.6709. Min Act: -0.1700
Data Index: 5697912 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.6709. Min Act: -0.1700
Data Index: 2068911 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.6709. Min Act: -0.1700
Data Index: 7067039 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.6084. Min Act: -0.1700
Data Index: 7852997 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.5772. Min Act: -0.1700
Data Index: 7580383 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.5147. Min Act: -0.1700
Data Index: 1532305 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.5147. Min Act: -0.1700
Data Index: 5351143 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.5147. Min Act: -0.1700
Data Index: 1574671 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.4834. Min Act: -0.1700
Data Index: 1532308 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.3272. Min Act: -0.1700
Data Index: 2936284 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.3272. Min Act: -0.1700
Data Index: 1797082 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.2647. Min Act: -0.1700
Data Index: 8206178 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.1397. Min Act: -0.1700
Data Index: 8712646 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.0459. Min Act: -0.1700
Data Index: 2437706 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.0147. Min Act: -0.1700
Data Index: 5017862 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.0147. Min Act: -0.1700
Data Index: 146996 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.0147. Min Act: -0.1700
Data Index: 6607474 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4834. Min Range: -8.4834
Max Act: 7.0147. Min Act: -0.1700
Data Index: 7825408 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19