Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4203 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.3487. Min Range: -15.3487
Max Act: 15.3487. Min Act: -0.1700
Data Index: 4364884 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.3487. Min Range: -15.3487
Max Act: 15.3487. Min Act: -0.1700
Data Index: 4272130 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.3487. Min Range: -15.3487
Max Act: 15.2237. Min Act: -0.1700
Data Index: 6820987 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.3487. Min Range: -15.3487
Max Act: 15.1612. Min Act: -0.1700
Data Index: 6586379 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.3487. Min Range: -15.3487
Max Act: 15.1612. Min Act: -0.1700
Data Index: 7414822 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.3487. Min Range: -15.3487
Max Act: 15.0362. Min Act: -0.1700
Data Index: 1169641 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.3487. Min Range: -15.3487
Max Act: 14.9737. Min Act: -0.1700
Data Index: 6414841 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.3487. Min Range: -15.3487
Max Act: 14.9737. Min Act: -0.1700
Data Index: 4892466 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.3487. Min Range: -15.3487
Max Act: 14.8487. Min Act: -0.1700
Data Index: 2209431 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.3487. Min Range: -15.3487
Max Act: 14.8487. Min Act: -0.1700
Data Index: 1474107 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.3487. Min Range: -15.3487
Max Act: 14.7862. Min Act: -0.1700
Data Index: 4731407 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.3487. Min Range: -15.3487
Max Act: 14.7862. Min Act: -0.1700
Data Index: 4540436 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.3487. Min Range: -15.3487
Max Act: 14.7862. Min Act: -0.1700
Data Index: 5448280 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.3487. Min Range: -15.3487
Max Act: 14.7862. Min Act: -0.1700
Data Index: 1423695 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.3487. Min Range: -15.3487
Max Act: 14.7862. Min Act: -0.1700
Data Index: 6812131 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.3487. Min Range: -15.3487
Max Act: 14.7237. Min Act: -0.1700
Data Index: 8444818 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.3487. Min Range: -15.3487
Max Act: 14.6612. Min Act: -0.1700
Data Index: 4927102 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.3487. Min Range: -15.3487
Max Act: 14.6612. Min Act: -0.1700
Data Index: 8814031 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.3487. Min Range: -15.3487
Max Act: 14.6612. Min Act: -0.1700
Data Index: 4919432 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.3487. Min Range: -15.3487
Max Act: 14.5987. Min Act: -0.1700
Data Index: 3127023 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19