Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3208 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1549. Min Range: -7.1549
Max Act: 7.1549. Min Act: -0.1700
Data Index: 5100617 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1549. Min Range: -7.1549
Max Act: 6.8424. Min Act: -0.1700
Data Index: 2374341 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1549. Min Range: -7.1549
Max Act: 6.7486. Min Act: -0.1700
Data Index: 331573 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1549. Min Range: -7.1549
Max Act: 6.7174. Min Act: -0.1700
Data Index: 439088 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1549. Min Range: -7.1549
Max Act: 6.6861. Min Act: -0.1700
Data Index: 1894452 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1549. Min Range: -7.1549
Max Act: 6.6861. Min Act: -0.1700
Data Index: 1684863 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1549. Min Range: -7.1549
Max Act: 6.6549. Min Act: -0.1700
Data Index: 2495470 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1549. Min Range: -7.1549
Max Act: 6.6236. Min Act: -0.1700
Data Index: 3881901 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1549. Min Range: -7.1549
Max Act: 6.6236. Min Act: -0.1700
Data Index: 1089069 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1549. Min Range: -7.1549
Max Act: 6.5611. Min Act: -0.1700
Data Index: 8696837 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1549. Min Range: -7.1549
Max Act: 6.5611. Min Act: -0.1700
Data Index: 33862 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1549. Min Range: -7.1549
Max Act: 6.5299. Min Act: -0.1700
Data Index: 7811281 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1549. Min Range: -7.1549
Max Act: 6.4986. Min Act: -0.1700
Data Index: 7918420 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1549. Min Range: -7.1549
Max Act: 6.4986. Min Act: -0.1700
Data Index: 1812914 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1549. Min Range: -7.1549
Max Act: 6.4986. Min Act: -0.1700
Data Index: 3420445 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1549. Min Range: -7.1549
Max Act: 6.4674. Min Act: -0.1700
Data Index: 2762356 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1549. Min Range: -7.1549
Max Act: 6.4361. Min Act: -0.1700
Data Index: 7496017 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1549. Min Range: -7.1549
Max Act: 6.4049. Min Act: -0.1700
Data Index: 5062407 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1549. Min Range: -7.1549
Max Act: 6.4049. Min Act: -0.1700
Data Index: 4990423 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1549. Min Range: -7.1549
Max Act: 6.3424. Min Act: -0.1700
Data Index: 8384202 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19