Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3353 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9511. Min Range: -3.9511
Max Act: 3.9511. Min Act: -0.1700
Data Index: 904041 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9511. Min Range: -3.9511
Max Act: 3.8886. Min Act: -0.1700
Data Index: 2479565 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9511. Min Range: -3.9511
Max Act: 3.8886. Min Act: -0.1700
Data Index: 6915467 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9511. Min Range: -3.9511
Max Act: 3.8573. Min Act: -0.1700
Data Index: 2720402 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9511. Min Range: -3.9511
Max Act: 3.8573. Min Act: -0.1700
Data Index: 3662304 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9511. Min Range: -3.9511
Max Act: 3.8886. Min Act: -0.1700
Data Index: 3104430 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9511. Min Range: -3.9511
Max Act: 3.8573. Min Act: -0.1700
Data Index: 1335041 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9511. Min Range: -3.9511
Max Act: 3.8261. Min Act: -0.1700
Data Index: 5877937 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9511. Min Range: -3.9511
Max Act: 3.7948. Min Act: -0.1700
Data Index: 2334420 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9511. Min Range: -3.9511
Max Act: 3.7635. Min Act: -0.1700
Data Index: 6162140 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9511. Min Range: -3.9511
Max Act: 3.7322. Min Act: -0.1700
Data Index: 528164 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9511. Min Range: -3.9511
Max Act: 3.7322. Min Act: -0.1700
Data Index: 4694223 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9511. Min Range: -3.9511
Max Act: 3.7322. Min Act: -0.1700
Data Index: 4500060 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9511. Min Range: -3.9511
Max Act: 3.6697. Min Act: -0.1700
Data Index: 6420606 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9511. Min Range: -3.9511
Max Act: 3.7009. Min Act: -0.1700
Data Index: 2240554 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9511. Min Range: -3.9511
Max Act: 3.7009. Min Act: -0.1700
Data Index: 2014778 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9511. Min Range: -3.9511
Max Act: 3.6697. Min Act: -0.1700
Data Index: 1727942 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9511. Min Range: -3.9511
Max Act: 3.7009. Min Act: -0.1700
Data Index: 6546193 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9511. Min Range: -3.9511
Max Act: 3.7009. Min Act: -0.1700
Data Index: 461010 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9511. Min Range: -3.9511
Max Act: 3.7009. Min Act: -0.1700
Data Index: 2527898 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19