Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3546 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7593. Min Range: -5.7593
Max Act: 5.7593. Min Act: -0.1700
Data Index: 1002353 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7593. Min Range: -5.7593
Max Act: 5.7593. Min Act: -0.1700
Data Index: 3105791 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7593. Min Range: -5.7593
Max Act: 5.6655. Min Act: -0.1700
Data Index: 4587324 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7593. Min Range: -5.7593
Max Act: 5.6655. Min Act: -0.1700
Data Index: 3724583 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7593. Min Range: -5.7593
Max Act: 5.6343. Min Act: -0.1700
Data Index: 1561051 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7593. Min Range: -5.7593
Max Act: 5.6030. Min Act: -0.1700
Data Index: 7855440 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7593. Min Range: -5.7593
Max Act: 5.6030. Min Act: -0.1700
Data Index: 8432152 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7593. Min Range: -5.7593
Max Act: 5.5718. Min Act: -0.1700
Data Index: 2928239 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7593. Min Range: -5.7593
Max Act: 5.5718. Min Act: -0.1700
Data Index: 5672244 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7593. Min Range: -5.7593
Max Act: 5.5718. Min Act: -0.1700
Data Index: 7977701 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7593. Min Range: -5.7593
Max Act: 5.5405. Min Act: -0.1700
Data Index: 5392469 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7593. Min Range: -5.7593
Max Act: 5.5405. Min Act: -0.1700
Data Index: 1243461 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7593. Min Range: -5.7593
Max Act: 5.5093. Min Act: -0.1700
Data Index: 8546674 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7593. Min Range: -5.7593
Max Act: 5.5093. Min Act: -0.1700
Data Index: 5866374 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7593. Min Range: -5.7593
Max Act: 5.5093. Min Act: -0.1700
Data Index: 760310 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7593. Min Range: -5.7593
Max Act: 5.5093. Min Act: -0.1700
Data Index: 3372684 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7593. Min Range: -5.7593
Max Act: 5.4780. Min Act: -0.1700
Data Index: 6041452 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7593. Min Range: -5.7593
Max Act: 5.5093. Min Act: -0.1700
Data Index: 6223462 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7593. Min Range: -5.7593
Max Act: 5.4780. Min Act: -0.1700
Data Index: 615363 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7593. Min Range: -5.7593
Max Act: 5.4780. Min Act: -0.1700
Data Index: 4336055 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19