Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4121 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3631. Min Range: -4.3631
Max Act: 4.3631. Min Act: -0.1700
Data Index: 2730218 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3631. Min Range: -4.3631
Max Act: 4.3318. Min Act: -0.1700
Data Index: 2755018 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3631. Min Range: -4.3631
Max Act: 4.2381. Min Act: -0.1700
Data Index: 8604547 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3631. Min Range: -4.3631
Max Act: 4.1756. Min Act: -0.1700
Data Index: 8385190 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3631. Min Range: -4.3631
Max Act: 4.2068. Min Act: -0.1700
Data Index: 3875150 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3631. Min Range: -4.3631
Max Act: 4.1756. Min Act: -0.1700
Data Index: 946612 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3631. Min Range: -4.3631
Max Act: 4.1756. Min Act: -0.1700
Data Index: 4303578 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3631. Min Range: -4.3631
Max Act: 4.1443. Min Act: -0.1700
Data Index: 8597000 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3631. Min Range: -4.3631
Max Act: 4.1443. Min Act: -0.1700
Data Index: 3892808 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3631. Min Range: -4.3631
Max Act: 4.1443. Min Act: -0.1700
Data Index: 3438490 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3631. Min Range: -4.3631
Max Act: 4.1443. Min Act: -0.1700
Data Index: 3344498 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3631. Min Range: -4.3631
Max Act: 4.1443. Min Act: -0.1700
Data Index: 2096549 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3631. Min Range: -4.3631
Max Act: 4.1443. Min Act: -0.1700
Data Index: 6516237 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3631. Min Range: -4.3631
Max Act: 4.2068. Min Act: -0.1700
Data Index: 6015564 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3631. Min Range: -4.3631
Max Act: 4.1443. Min Act: -0.1700
Data Index: 5633190 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3631. Min Range: -4.3631
Max Act: 4.1131. Min Act: -0.1700
Data Index: 2562901 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3631. Min Range: -4.3631
Max Act: 4.0818. Min Act: -0.1700
Data Index: 3722438 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3631. Min Range: -4.3631
Max Act: 4.1131. Min Act: -0.1700
Data Index: 8158068 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3631. Min Range: -4.3631
Max Act: 4.1131. Min Act: -0.1700
Data Index: 3529110 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3631. Min Range: -4.3631
Max Act: 4.0818. Min Act: -0.1700
Data Index: 1540055 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19