Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 427 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.9850. Min Act: -0.1700
Data Index: 5624852 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.8288. Min Act: -0.1700
Data Index: 4149659 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.8288. Min Act: -0.1700
Data Index: 3858066 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.7038. Min Act: -0.1700
Data Index: 4823177 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.7038. Min Act: -0.1700
Data Index: 1295751 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.6413. Min Act: -0.1700
Data Index: 823618 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.6413. Min Act: -0.1700
Data Index: 875293 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.6413. Min Act: -0.1700
Data Index: 7989499 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.6413. Min Act: -0.1700
Data Index: 1886414 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.6413. Min Act: -0.1700
Data Index: 7240831 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.6100. Min Act: -0.1700
Data Index: 5603999 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.6100. Min Act: -0.1700
Data Index: 508323 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.6100. Min Act: -0.1700
Data Index: 2312148 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.5788. Min Act: -0.1700
Data Index: 4853639 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.5788. Min Act: -0.1700
Data Index: 1075299 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.5475. Min Act: -0.1700
Data Index: 1271920 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.5163. Min Act: -0.1700
Data Index: 4020256 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.5163. Min Act: -0.1700
Data Index: 6507015 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.5163. Min Act: -0.1700
Data Index: 5415888 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9850. Min Range: -4.9850
Max Act: 4.4850. Min Act: -0.1700
Data Index: 4016803 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19