Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2104 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7108. Min Range: -5.7108
Max Act: 5.7108. Min Act: -0.1700
Data Index: 2191380 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7108. Min Range: -5.7108
Max Act: 5.6483. Min Act: -0.1700
Data Index: 2390208 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7108. Min Range: -5.7108
Max Act: 5.6483. Min Act: -0.1700
Data Index: 6090172 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7108. Min Range: -5.7108
Max Act: 5.3358. Min Act: -0.1700
Data Index: 4052548 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7108. Min Range: -5.7108
Max Act: 5.3670. Min Act: -0.1700
Data Index: 341888 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7108. Min Range: -5.7108
Max Act: 5.2420. Min Act: -0.1700
Data Index: 1123079 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7108. Min Range: -5.7108
Max Act: 5.1170. Min Act: -0.1700
Data Index: 7608182 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7108. Min Range: -5.7108
Max Act: 5.0233. Min Act: -0.1700
Data Index: 655587 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7108. Min Range: -5.7108
Max Act: 4.9920. Min Act: -0.1700
Data Index: 1157536 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7108. Min Range: -5.7108
Max Act: 4.9920. Min Act: -0.1700
Data Index: 5040822 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7108. Min Range: -5.7108
Max Act: 4.8670. Min Act: -0.1700
Data Index: 4453987 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7108. Min Range: -5.7108
Max Act: 4.9295. Min Act: -0.1700
Data Index: 4956987 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7108. Min Range: -5.7108
Max Act: 4.8983. Min Act: -0.1700
Data Index: 1625558 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7108. Min Range: -5.7108
Max Act: 4.8983. Min Act: -0.1700
Data Index: 5159415 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7108. Min Range: -5.7108
Max Act: 4.8670. Min Act: -0.1700
Data Index: 8486959 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7108. Min Range: -5.7108
Max Act: 4.8670. Min Act: -0.1700
Data Index: 1547007 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7108. Min Range: -5.7108
Max Act: 4.8358. Min Act: -0.1700
Data Index: 401510 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7108. Min Range: -5.7108
Max Act: 4.8358. Min Act: -0.1700
Data Index: 7041542 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7108. Min Range: -5.7108
Max Act: 4.8670. Min Act: -0.1700
Data Index: 3816671 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7108. Min Range: -5.7108
Max Act: 4.8358. Min Act: -0.1700
Data Index: 3826862 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19