Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 218 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4038. Min Range: -6.4038
Max Act: 6.4038. Min Act: -0.1700
Data Index: 459854 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4038. Min Range: -6.4038
Max Act: 5.7788. Min Act: -0.1700
Data Index: 4510005 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4038. Min Range: -6.4038
Max Act: 5.8100. Min Act: -0.1700
Data Index: 7414058 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4038. Min Range: -6.4038
Max Act: 5.7788. Min Act: -0.1700
Data Index: 4123324 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4038. Min Range: -6.4038
Max Act: 5.7788. Min Act: -0.1700
Data Index: 8618117 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4038. Min Range: -6.4038
Max Act: 5.7163. Min Act: -0.1700
Data Index: 4153465 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4038. Min Range: -6.4038
Max Act: 5.6538. Min Act: -0.1700
Data Index: 6681674 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4038. Min Range: -6.4038
Max Act: 5.6850. Min Act: -0.1700
Data Index: 7222470 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4038. Min Range: -6.4038
Max Act: 5.6538. Min Act: -0.1700
Data Index: 3526688 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4038. Min Range: -6.4038
Max Act: 5.6225. Min Act: -0.1700
Data Index: 182807 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4038. Min Range: -6.4038
Max Act: 5.6225. Min Act: -0.1700
Data Index: 3088985 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4038. Min Range: -6.4038
Max Act: 5.5913. Min Act: -0.1700
Data Index: 3211145 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4038. Min Range: -6.4038
Max Act: 5.5913. Min Act: -0.1700
Data Index: 500446 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4038. Min Range: -6.4038
Max Act: 5.5600. Min Act: -0.1700
Data Index: 3094331 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4038. Min Range: -6.4038
Max Act: 5.5600. Min Act: -0.1700
Data Index: 3090771 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4038. Min Range: -6.4038
Max Act: 5.5600. Min Act: -0.1700
Data Index: 8304452 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4038. Min Range: -6.4038
Max Act: 5.5600. Min Act: -0.1700
Data Index: 2445010 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4038. Min Range: -6.4038
Max Act: 5.5600. Min Act: -0.1700
Data Index: 1649514 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4038. Min Range: -6.4038
Max Act: 5.5288. Min Act: -0.1700
Data Index: 3441117 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4038. Min Range: -6.4038
Max Act: 5.5600. Min Act: -0.1700
Data Index: 3412428 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19