Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1915 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2721. Min Range: -6.2721
Max Act: 6.2721. Min Act: -0.1700
Data Index: 3838299 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2721. Min Range: -6.2721
Max Act: 6.0221. Min Act: -0.1700
Data Index: 2388830 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.8971. Min Act: -0.1700
Data Index: 6170117 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.8971. Min Act: -0.1700
Data Index: 8615683 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.8346. Min Act: -0.1700
Data Index: 7115449 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.8346. Min Act: -0.1700
Data Index: 6758908 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.8033. Min Act: -0.1700
Data Index: 3058920 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.8033. Min Act: -0.1700
Data Index: 399815 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.8346. Min Act: -0.1700
Data Index: 5731747 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.7721. Min Act: -0.1700
Data Index: 2365275 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.7721. Min Act: -0.1700
Data Index: 1772634 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.7721. Min Act: -0.1700
Data Index: 522414 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.8033. Min Act: -0.1700
Data Index: 4706303 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.7408. Min Act: -0.1700
Data Index: 3794655 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.7408. Min Act: -0.1700
Data Index: 3150138 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.7408. Min Act: -0.1700
Data Index: 3669071 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.7408. Min Act: -0.1700
Data Index: 4682489 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.7408. Min Act: -0.1700
Data Index: 2685149 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.7096. Min Act: -0.1700
Data Index: 6454792 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2721. Min Range: -6.2721
Max Act: 5.7096. Min Act: -0.1700
Data Index: 437590 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19