Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4571 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0332. Min Range: -5.0332
Max Act: 5.0332. Min Act: -0.1700
Data Index: 6935967 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0332. Min Range: -5.0332
Max Act: 5.0332. Min Act: -0.1700
Data Index: 2140036 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0332. Min Range: -5.0332
Max Act: 5.0020. Min Act: -0.1700
Data Index: 5236069 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.9707. Min Act: -0.1700
Data Index: 8504821 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.9707. Min Act: -0.1700
Data Index: 3441487 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.9707. Min Act: -0.1700
Data Index: 5039261 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.9395. Min Act: -0.1700
Data Index: 4911097 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.9395. Min Act: -0.1700
Data Index: 2167727 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.9395. Min Act: -0.1700
Data Index: 6870689 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.9395. Min Act: -0.1700
Data Index: 6151939 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.9395. Min Act: -0.1700
Data Index: 3933545 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.9395. Min Act: -0.1700
Data Index: 1621437 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.9395. Min Act: -0.1700
Data Index: 3817359 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.9395. Min Act: -0.1700
Data Index: 3262359 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.9395. Min Act: -0.1700
Data Index: 2195344 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.9082. Min Act: -0.1700
Data Index: 149099 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.9082. Min Act: -0.1700
Data Index: 919618 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.9082. Min Act: -0.1700
Data Index: 64276 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.9082. Min Act: -0.1700
Data Index: 5383120 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0332. Min Range: -5.0332
Max Act: 4.9082. Min Act: -0.1700
Data Index: 6092935 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19