Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 37 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0667. Min Range: -7.0667
Max Act: 7.0667. Min Act: -0.1700
Data Index: 50674 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0667. Min Range: -7.0667
Max Act: 6.8792. Min Act: -0.1700
Data Index: 6234152 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0667. Min Range: -7.0667
Max Act: 6.8792. Min Act: -0.1700
Data Index: 1994537 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0667. Min Range: -7.0667
Max Act: 6.8479. Min Act: -0.1700
Data Index: 7534440 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0667. Min Range: -7.0667
Max Act: 6.8479. Min Act: -0.1700
Data Index: 2524071 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0667. Min Range: -7.0667
Max Act: 6.8167. Min Act: -0.1700
Data Index: 1183548 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0667. Min Range: -7.0667
Max Act: 6.8479. Min Act: -0.1700
Data Index: 4230344 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0667. Min Range: -7.0667
Max Act: 6.8479. Min Act: -0.1700
Data Index: 5587273 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0667. Min Range: -7.0667
Max Act: 6.8479. Min Act: -0.1700
Data Index: 6531845 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0667. Min Range: -7.0667
Max Act: 6.7854. Min Act: -0.1700
Data Index: 1536990 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0667. Min Range: -7.0667
Max Act: 6.7854. Min Act: -0.1700
Data Index: 2380100 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0667. Min Range: -7.0667
Max Act: 6.7229. Min Act: -0.1700
Data Index: 2623137 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0667. Min Range: -7.0667
Max Act: 6.7229. Min Act: -0.1700
Data Index: 7504900 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0667. Min Range: -7.0667
Max Act: 6.6917. Min Act: -0.1700
Data Index: 2526495 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0667. Min Range: -7.0667
Max Act: 6.6917. Min Act: -0.1700
Data Index: 3238046 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0667. Min Range: -7.0667
Max Act: 6.6917. Min Act: -0.1700
Data Index: 5606487 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0667. Min Range: -7.0667
Max Act: 6.7229. Min Act: -0.1700
Data Index: 424826 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0667. Min Range: -7.0667
Max Act: 6.6604. Min Act: -0.1700
Data Index: 3312809 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0667. Min Range: -7.0667
Max Act: 6.6604. Min Act: -0.1700
Data Index: 2628966 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0667. Min Range: -7.0667
Max Act: 6.6604. Min Act: -0.1700
Data Index: 1338023 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19