Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2147 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4006. Min Range: -3.4006
Max Act: 3.4006. Min Act: -0.1700
Data Index: 1644231 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4006. Min Range: -3.4006
Max Act: 3.3065. Min Act: -0.1700
Data Index: 2601055 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4006. Min Range: -3.4006
Max Act: 3.2751. Min Act: -0.1700
Data Index: 5589739 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4006. Min Range: -3.4006
Max Act: 3.2594. Min Act: -0.1700
Data Index: 8313282 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4006. Min Range: -3.4006
Max Act: 3.2594. Min Act: -0.1700
Data Index: 1305572 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4006. Min Range: -3.4006
Max Act: 3.2437. Min Act: -0.1700
Data Index: 317753 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4006. Min Range: -3.4006
Max Act: 3.2279. Min Act: -0.1700
Data Index: 4105360 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4006. Min Range: -3.4006
Max Act: 3.2122. Min Act: -0.1700
Data Index: 4750591 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4006. Min Range: -3.4006
Max Act: 3.1965. Min Act: -0.1700
Data Index: 5359393 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4006. Min Range: -3.4006
Max Act: 3.1808. Min Act: -0.1700
Data Index: 7355396 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4006. Min Range: -3.4006
Max Act: 3.1650. Min Act: -0.1700
Data Index: 1506172 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4006. Min Range: -3.4006
Max Act: 3.1336. Min Act: -0.1700
Data Index: 4972525 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4006. Min Range: -3.4006
Max Act: 3.1336. Min Act: -0.1700
Data Index: 3566125 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4006. Min Range: -3.4006
Max Act: 3.1178. Min Act: -0.1700
Data Index: 4328199 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4006. Min Range: -3.4006
Max Act: 3.1178. Min Act: -0.1700
Data Index: 7477046 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4006. Min Range: -3.4006
Max Act: 3.1178. Min Act: -0.1700
Data Index: 3405627 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4006. Min Range: -3.4006
Max Act: 3.0705. Min Act: -0.1700
Data Index: 2378997 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4006. Min Range: -3.4006
Max Act: 3.0863. Min Act: -0.1700
Data Index: 2271292 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4006. Min Range: -3.4006
Max Act: 3.0863. Min Act: -0.1700
Data Index: 5306423 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4006. Min Range: -3.4006
Max Act: 3.0705. Min Act: -0.1700
Data Index: 363055 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19