Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2254 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0700. Min Range: -6.0700
Max Act: 6.0700. Min Act: -0.1700
Data Index: 3941155 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0700. Min Range: -6.0700
Max Act: 6.0075. Min Act: -0.1700
Data Index: 1536900 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0700. Min Range: -6.0700
Max Act: 5.9137. Min Act: -0.1700
Data Index: 5689946 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0700. Min Range: -6.0700
Max Act: 5.8200. Min Act: -0.1700
Data Index: 6517082 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0700. Min Range: -6.0700
Max Act: 5.8200. Min Act: -0.1700
Data Index: 6627538 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0700. Min Range: -6.0700
Max Act: 5.7887. Min Act: -0.1700
Data Index: 2774086 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0700. Min Range: -6.0700
Max Act: 5.7887. Min Act: -0.1700
Data Index: 1049911 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0700. Min Range: -6.0700
Max Act: 5.7887. Min Act: -0.1700
Data Index: 7114169 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0700. Min Range: -6.0700
Max Act: 5.7887. Min Act: -0.1700
Data Index: 1136815 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0700. Min Range: -6.0700
Max Act: 5.7575. Min Act: -0.1700
Data Index: 965618 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0700. Min Range: -6.0700
Max Act: 5.7887. Min Act: -0.1698
Data Index: 5690521 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0700. Min Range: -6.0700
Max Act: 5.7575. Min Act: -0.1700
Data Index: 5148387 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0700. Min Range: -6.0700
Max Act: 5.7575. Min Act: -0.1700
Data Index: 3946512 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0700. Min Range: -6.0700
Max Act: 5.7575. Min Act: -0.1700
Data Index: 2137502 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0700. Min Range: -6.0700
Max Act: 5.6950. Min Act: -0.1700
Data Index: 6627541 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0700. Min Range: -6.0700
Max Act: 5.6950. Min Act: -0.1700
Data Index: 1722599 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0700. Min Range: -6.0700
Max Act: 5.6637. Min Act: -0.1700
Data Index: 5944111 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0700. Min Range: -6.0700
Max Act: 5.6325. Min Act: -0.1700
Data Index: 3417270 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0700. Min Range: -6.0700
Max Act: 5.6325. Min Act: -0.1700
Data Index: 4766392 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0700. Min Range: -6.0700
Max Act: 5.6325. Min Act: -0.1700
Data Index: 1137183 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19