Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3262 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.9554. Min Act: -0.1700
Data Index: 3640753 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.8929. Min Act: -0.1700
Data Index: 6227038 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.8616. Min Act: -0.1700
Data Index: 7541478 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.7991. Min Act: -0.1700
Data Index: 6228564 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.7679. Min Act: -0.1700
Data Index: 1379632 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.7366. Min Act: -0.1700
Data Index: 1307635 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.7366. Min Act: -0.1700
Data Index: 436662 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.7054. Min Act: -0.1700
Data Index: 5352343 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.7054. Min Act: -0.1700
Data Index: 3096907 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.7054. Min Act: -0.1700
Data Index: 8456355 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.7054. Min Act: -0.1700
Data Index: 6997466 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.7054. Min Act: -0.1700
Data Index: 2951488 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.6741. Min Act: -0.1700
Data Index: 3820427 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.6741. Min Act: -0.1700
Data Index: 7754789 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.6741. Min Act: -0.1700
Data Index: 595385 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.6741. Min Act: -0.1700
Data Index: 5064436 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.6741. Min Act: -0.1700
Data Index: 8627408 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.6429. Min Act: -0.1700
Data Index: 1886326 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.6429. Min Act: -0.1700
Data Index: 1610375 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.6429. Min Act: -0.1700
Data Index: 2409603 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19