Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2754 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4107. Min Range: -6.4107
Max Act: 6.4107. Min Act: -0.1700
Data Index: 7892337 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4107. Min Range: -6.4107
Max Act: 6.2857. Min Act: -0.1700
Data Index: 567643 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4107. Min Range: -6.4107
Max Act: 6.2232. Min Act: -0.1700
Data Index: 6461833 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4107. Min Range: -6.4107
Max Act: 6.1919. Min Act: -0.1700
Data Index: 5947960 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4107. Min Range: -6.4107
Max Act: 5.9732. Min Act: -0.1700
Data Index: 5149956 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4107. Min Range: -6.4107
Max Act: 5.9732. Min Act: -0.1700
Data Index: 230453 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4107. Min Range: -6.4107
Max Act: 5.9732. Min Act: -0.1700
Data Index: 2956472 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4107. Min Range: -6.4107
Max Act: 5.9732. Min Act: -0.1700
Data Index: 2027345 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4107. Min Range: -6.4107
Max Act: 5.9419. Min Act: -0.1700
Data Index: 1335344 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4107. Min Range: -6.4107
Max Act: 5.9419. Min Act: -0.1700
Data Index: 8493786 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4107. Min Range: -6.4107
Max Act: 5.9107. Min Act: -0.1700
Data Index: 4134401 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4107. Min Range: -6.4107
Max Act: 5.9419. Min Act: -0.1700
Data Index: 6713374 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4107. Min Range: -6.4107
Max Act: 5.8794. Min Act: -0.1700
Data Index: 1788247 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4107. Min Range: -6.4107
Max Act: 5.8794. Min Act: -0.1700
Data Index: 265854 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4107. Min Range: -6.4107
Max Act: 5.8482. Min Act: -0.1700
Data Index: 6125331 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4107. Min Range: -6.4107
Max Act: 5.8482. Min Act: -0.1700
Data Index: 7647817 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4107. Min Range: -6.4107
Max Act: 5.8482. Min Act: -0.1700
Data Index: 5177446 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4107. Min Range: -6.4107
Max Act: 5.8169. Min Act: -0.1700
Data Index: 5623252 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4107. Min Range: -6.4107
Max Act: 5.7857. Min Act: -0.1700
Data Index: 7472499 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4107. Min Range: -6.4107
Max Act: 5.7544. Min Act: -0.1700
Data Index: 524215 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19