Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4604 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4448. Min Range: -6.4448
Max Act: 6.4448. Min Act: -0.1700
Data Index: 1609794 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4448. Min Range: -6.4448
Max Act: 6.3511. Min Act: -0.1700
Data Index: 6232457 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4448. Min Range: -6.4448
Max Act: 6.3511. Min Act: -0.1700
Data Index: 5938950 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4448. Min Range: -6.4448
Max Act: 6.3198. Min Act: -0.1700
Data Index: 2453987 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4448. Min Range: -6.4448
Max Act: 6.3198. Min Act: -0.1700
Data Index: 7011627 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4448. Min Range: -6.4448
Max Act: 6.2573. Min Act: -0.1700
Data Index: 6997497 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4448. Min Range: -6.4448
Max Act: 6.2886. Min Act: -0.1700
Data Index: 5707470 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4448. Min Range: -6.4448
Max Act: 6.2261. Min Act: -0.1700
Data Index: 1378581 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4448. Min Range: -6.4448
Max Act: 6.2261. Min Act: -0.1700
Data Index: 2492704 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4448. Min Range: -6.4448
Max Act: 6.1948. Min Act: -0.1700
Data Index: 4941869 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4448. Min Range: -6.4448
Max Act: 6.1948. Min Act: -0.1700
Data Index: 8545680 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4448. Min Range: -6.4448
Max Act: 6.1948. Min Act: -0.1700
Data Index: 4166971 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4448. Min Range: -6.4448
Max Act: 6.1636. Min Act: -0.1700
Data Index: 2763991 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4448. Min Range: -6.4448
Max Act: 6.1323. Min Act: -0.1700
Data Index: 7060574 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4448. Min Range: -6.4448
Max Act: 6.1323. Min Act: -0.1700
Data Index: 1205515 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4448. Min Range: -6.4448
Max Act: 6.1011. Min Act: -0.1700
Data Index: 1452564 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4448. Min Range: -6.4448
Max Act: 6.0698. Min Act: -0.1700
Data Index: 4657540 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4448. Min Range: -6.4448
Max Act: 6.0698. Min Act: -0.1700
Data Index: 6451239 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4448. Min Range: -6.4448
Max Act: 6.0386. Min Act: -0.1700
Data Index: 5360088 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4448. Min Range: -6.4448
Max Act: 6.0386. Min Act: -0.1700
Data Index: 6595320 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19