Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4967 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2256. Min Range: -6.2256
Max Act: 6.2256. Min Act: -0.1700
Data Index: 5368172 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2256. Min Range: -6.2256
Max Act: 6.2256. Min Act: -0.1700
Data Index: 5241617 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2256. Min Range: -6.2256
Max Act: 6.1006. Min Act: -0.1700
Data Index: 8241153 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2256. Min Range: -6.2256
Max Act: 6.0693. Min Act: -0.1700
Data Index: 2266882 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2256. Min Range: -6.2256
Max Act: 6.0068. Min Act: -0.1700
Data Index: 4252468 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2256. Min Range: -6.2256
Max Act: 6.0381. Min Act: -0.1700
Data Index: 4536193 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2256. Min Range: -6.2256
Max Act: 5.9443. Min Act: -0.1700
Data Index: 1032294 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2256. Min Range: -6.2256
Max Act: 5.9443. Min Act: -0.1700
Data Index: 7727116 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2256. Min Range: -6.2256
Max Act: 5.9131. Min Act: -0.1700
Data Index: 7597473 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2256. Min Range: -6.2256
Max Act: 5.8818. Min Act: -0.1700
Data Index: 6583368 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2256. Min Range: -6.2256
Max Act: 5.9131. Min Act: -0.1700
Data Index: 8378068 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2256. Min Range: -6.2256
Max Act: 5.9131. Min Act: -0.1700
Data Index: 3164953 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2256. Min Range: -6.2256
Max Act: 5.9131. Min Act: -0.1700
Data Index: 7668775 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2256. Min Range: -6.2256
Max Act: 5.8818. Min Act: -0.1700
Data Index: 7037772 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2256. Min Range: -6.2256
Max Act: 5.8818. Min Act: -0.1700
Data Index: 7429067 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2256. Min Range: -6.2256
Max Act: 5.8818. Min Act: -0.1700
Data Index: 8168247 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2256. Min Range: -6.2256
Max Act: 5.8818. Min Act: -0.1700
Data Index: 6378194 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2256. Min Range: -6.2256
Max Act: 5.8506. Min Act: -0.1700
Data Index: 2374054 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2256. Min Range: -6.2256
Max Act: 5.8506. Min Act: -0.1700
Data Index: 383085 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2256. Min Range: -6.2256
Max Act: 5.8506. Min Act: -0.1700
Data Index: 1083922 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19