Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2491 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.7913. Min Act: -0.1700
Data Index: 4094269 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.8225. Min Act: -0.1700
Data Index: 2663142 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.7913. Min Act: -0.1700
Data Index: 3243510 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.7600. Min Act: -0.1700
Data Index: 1759778 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.7288. Min Act: -0.1700
Data Index: 5899883 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.6663. Min Act: -0.1700
Data Index: 363394 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.6975. Min Act: -0.1700
Data Index: 6481631 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.6975. Min Act: -0.1700
Data Index: 854261 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.6663. Min Act: -0.1700
Data Index: 4959748 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.6663. Min Act: -0.1700
Data Index: 7479838 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.5725. Min Act: -0.1700
Data Index: 6071573 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.5100. Min Act: -0.1700
Data Index: 249826 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.5100. Min Act: -0.1700
Data Index: 2707429 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.4788. Min Act: -0.1700
Data Index: 802532 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.4788. Min Act: -0.1700
Data Index: 1312511 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.5100. Min Act: -0.1700
Data Index: 7479840 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.4788. Min Act: -0.1700
Data Index: 4463413 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.4788. Min Act: -0.1700
Data Index: 3035422 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.4475. Min Act: -0.1700
Data Index: 1816397 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8225. Min Range: -4.8225
Max Act: 4.4475. Min Act: -0.1700
Data Index: 5066227 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19