Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 533 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7925. Min Range: -6.7925
Max Act: 6.7925. Min Act: -0.1700
Data Index: 3362746 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7925. Min Range: -6.7925
Max Act: 6.7612. Min Act: -0.1700
Data Index: 8160974 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7925. Min Range: -6.7925
Max Act: 6.6675. Min Act: -0.1700
Data Index: 5918409 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7925. Min Range: -6.7925
Max Act: 6.6675. Min Act: -0.1700
Data Index: 5935472 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7925. Min Range: -6.7925
Max Act: 6.5737. Min Act: -0.1700
Data Index: 4569809 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7925. Min Range: -6.7925
Max Act: 6.5737. Min Act: -0.1700
Data Index: 4408409 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7925. Min Range: -6.7925
Max Act: 6.5425. Min Act: -0.1700
Data Index: 7910934 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7925. Min Range: -6.7925
Max Act: 6.5425. Min Act: -0.1700
Data Index: 644668 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7925. Min Range: -6.7925
Max Act: 6.4800. Min Act: -0.1700
Data Index: 6200638 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7925. Min Range: -6.7925
Max Act: 6.4800. Min Act: -0.1700
Data Index: 1135046 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7925. Min Range: -6.7925
Max Act: 6.3862. Min Act: -0.1700
Data Index: 4036597 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7925. Min Range: -6.7925
Max Act: 6.4487. Min Act: -0.1700
Data Index: 406147 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7925. Min Range: -6.7925
Max Act: 6.2612. Min Act: -0.1700
Data Index: 6609912 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7925. Min Range: -6.7925
Max Act: 6.2300. Min Act: -0.1700
Data Index: 6806175 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7925. Min Range: -6.7925
Max Act: 6.1987. Min Act: -0.1700
Data Index: 4503914 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7925. Min Range: -6.7925
Max Act: 6.1987. Min Act: -0.1700
Data Index: 8561906 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7925. Min Range: -6.7925
Max Act: 6.2300. Min Act: -0.1700
Data Index: 8584191 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7925. Min Range: -6.7925
Max Act: 6.1050. Min Act: -0.1700
Data Index: 248992 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7925. Min Range: -6.7925
Max Act: 6.1362. Min Act: -0.1700
Data Index: 747544 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7925. Min Range: -6.7925
Max Act: 6.0737. Min Act: -0.1700
Data Index: 5506395 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19