Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5357 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.3679. Min Act: -0.1700
Data Index: 7183593 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.2429. Min Act: -0.1700
Data Index: 5089056 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.2429. Min Act: -0.1700
Data Index: 8798479 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.1492. Min Act: -0.1700
Data Index: 8252990 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.0867. Min Act: -0.1700
Data Index: 2061494 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.0554. Min Act: -0.1700
Data Index: 2226878 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.0554. Min Act: -0.1700
Data Index: 1112517 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.0242. Min Act: -0.1700
Data Index: 1493870 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.0242. Min Act: -0.1700
Data Index: 8537698 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3679. Min Range: -5.3679
Max Act: 4.9929. Min Act: -0.1700
Data Index: 4212429 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.0554. Min Act: -0.1700
Data Index: 3010162 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.0242. Min Act: -0.1700
Data Index: 8797716 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.0242. Min Act: -0.1700
Data Index: 3254426 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.0242. Min Act: -0.1700
Data Index: 5832671 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3679. Min Range: -5.3679
Max Act: 5.0242. Min Act: -0.1700
Data Index: 2471152 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3679. Min Range: -5.3679
Max Act: 4.9929. Min Act: -0.1700
Data Index: 515302 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3679. Min Range: -5.3679
Max Act: 4.9929. Min Act: -0.1700
Data Index: 629863 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3679. Min Range: -5.3679
Max Act: 4.9617. Min Act: -0.1700
Data Index: 6302743 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3679. Min Range: -5.3679
Max Act: 4.9304. Min Act: -0.1700
Data Index: 3737079 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3679. Min Range: -5.3679
Max Act: 4.9304. Min Act: -0.1700
Data Index: 4977242 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19