Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4516 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7907. Min Range: -5.7907
Max Act: 5.7907. Min Act: -0.1700
Data Index: 782745 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7907. Min Range: -5.7907
Max Act: 5.7282. Min Act: -0.1700
Data Index: 8164112 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7907. Min Range: -5.7907
Max Act: 5.6970. Min Act: -0.1700
Data Index: 1537170 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7907. Min Range: -5.7907
Max Act: 5.5720. Min Act: -0.1700
Data Index: 8744604 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7907. Min Range: -5.7907
Max Act: 5.5407. Min Act: -0.1700
Data Index: 1453308 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7907. Min Range: -5.7907
Max Act: 5.5407. Min Act: -0.1700
Data Index: 1581794 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7907. Min Range: -5.7907
Max Act: 5.5720. Min Act: -0.1700
Data Index: 3069608 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7907. Min Range: -5.7907
Max Act: 5.4470. Min Act: -0.1700
Data Index: 8744573 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7907. Min Range: -5.7907
Max Act: 5.4470. Min Act: -0.1700
Data Index: 1776378 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7907. Min Range: -5.7907
Max Act: 5.4470. Min Act: -0.1700
Data Index: 1640021 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7907. Min Range: -5.7907
Max Act: 5.4470. Min Act: -0.1700
Data Index: 1020688 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7907. Min Range: -5.7907
Max Act: 5.4470. Min Act: -0.1700
Data Index: 8421857 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7907. Min Range: -5.7907
Max Act: 5.4157. Min Act: -0.1700
Data Index: 6123746 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7907. Min Range: -5.7907
Max Act: 5.4157. Min Act: -0.1700
Data Index: 4133603 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7907. Min Range: -5.7907
Max Act: 5.3845. Min Act: -0.1700
Data Index: 8491285 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7907. Min Range: -5.7907
Max Act: 5.4157. Min Act: -0.1700
Data Index: 3377135 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7907. Min Range: -5.7907
Max Act: 5.3532. Min Act: -0.1700
Data Index: 4003965 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7907. Min Range: -5.7907
Max Act: 5.3532. Min Act: -0.1700
Data Index: 4888261 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7907. Min Range: -5.7907
Max Act: 5.3532. Min Act: -0.1700
Data Index: 7995344 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7907. Min Range: -5.7907
Max Act: 5.3532. Min Act: -0.1700
Data Index: 8421864 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19