Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2975 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3001. Min Range: -5.3001
Max Act: 5.3001. Min Act: -0.1700
Data Index: 576406 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3001. Min Range: -5.3001
Max Act: 5.2688. Min Act: -0.1700
Data Index: 5481691 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3001. Min Range: -5.3001
Max Act: 5.1751. Min Act: -0.1700
Data Index: 6071860 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3001. Min Range: -5.3001
Max Act: 5.0188. Min Act: -0.1700
Data Index: 5015901 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.9251. Min Act: -0.1700
Data Index: 7147678 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.9251. Min Act: -0.1700
Data Index: 8441721 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.9251. Min Act: -0.1700
Data Index: 5242508 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.8938. Min Act: -0.1700
Data Index: 5284207 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.8938. Min Act: -0.1700
Data Index: 1995127 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.8626. Min Act: -0.1700
Data Index: 2112064 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.8626. Min Act: -0.1700
Data Index: 5470345 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.8313. Min Act: -0.1700
Data Index: 5569955 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.8626. Min Act: -0.1700
Data Index: 8513438 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.8313. Min Act: -0.1700
Data Index: 2674102 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.8313. Min Act: -0.1700
Data Index: 6936326 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.8313. Min Act: -0.1700
Data Index: 4235405 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.8001. Min Act: -0.1700
Data Index: 1156720 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.8313. Min Act: -0.1700
Data Index: 3923731 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.8313. Min Act: -0.1700
Data Index: 4697590 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3001. Min Range: -5.3001
Max Act: 4.8001. Min Act: -0.1700
Data Index: 1370339 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19