Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4901 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9107. Min Range: -5.9107
Max Act: 5.9107. Min Act: -0.1700
Data Index: 928883 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9107. Min Range: -5.9107
Max Act: 5.6920. Min Act: -0.1700
Data Index: 5983786 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9107. Min Range: -5.9107
Max Act: 5.6607. Min Act: -0.1700
Data Index: 3649189 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9107. Min Range: -5.9107
Max Act: 5.6607. Min Act: -0.1700
Data Index: 4022579 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9107. Min Range: -5.9107
Max Act: 5.6295. Min Act: -0.1700
Data Index: 4788365 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9107. Min Range: -5.9107
Max Act: 5.6295. Min Act: -0.1700
Data Index: 928884 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9107. Min Range: -5.9107
Max Act: 5.5982. Min Act: -0.1700
Data Index: 928886 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9107. Min Range: -5.9107
Max Act: 5.5670. Min Act: -0.1700
Data Index: 6064840 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9107. Min Range: -5.9107
Max Act: 5.5670. Min Act: -0.1700
Data Index: 2345598 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9107. Min Range: -5.9107
Max Act: 5.5670. Min Act: -0.1700
Data Index: 645080 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9107. Min Range: -5.9107
Max Act: 5.5670. Min Act: -0.1700
Data Index: 8306697 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9107. Min Range: -5.9107
Max Act: 5.5670. Min Act: -0.1700
Data Index: 4637580 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9107. Min Range: -5.9107
Max Act: 5.5357. Min Act: -0.1700
Data Index: 1284717 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9107. Min Range: -5.9107
Max Act: 5.5357. Min Act: -0.1700
Data Index: 6767393 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9107. Min Range: -5.9107
Max Act: 5.5670. Min Act: -0.1700
Data Index: 928881 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9107. Min Range: -5.9107
Max Act: 5.5357. Min Act: -0.1700
Data Index: 2712316 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9107. Min Range: -5.9107
Max Act: 5.5357. Min Act: -0.1700
Data Index: 2328535 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9107. Min Range: -5.9107
Max Act: 5.5357. Min Act: -0.1700
Data Index: 277236 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9107. Min Range: -5.9107
Max Act: 5.5045. Min Act: -0.1700
Data Index: 3060395 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9107. Min Range: -5.9107
Max Act: 5.5357. Min Act: -0.1700
Data Index: 8266302 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19