Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2585 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4115. Min Range: -9.4115
Max Act: 9.4115. Min Act: -0.1700
Data Index: 2013156 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4115. Min Range: -9.4115
Max Act: 9.0365. Min Act: -0.1700
Data Index: 3035189 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4115. Min Range: -9.4115
Max Act: 8.8490. Min Act: -0.1700
Data Index: 5678508 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4115. Min Range: -9.4115
Max Act: 8.7865. Min Act: -0.1700
Data Index: 27143 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4115. Min Range: -9.4115
Max Act: 8.6615. Min Act: -0.1700
Data Index: 976912 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4115. Min Range: -9.4115
Max Act: 8.5990. Min Act: -0.1700
Data Index: 8190961 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4115. Min Range: -9.4115
Max Act: 8.4740. Min Act: -0.1700
Data Index: 8564891 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4115. Min Range: -9.4115
Max Act: 8.4740. Min Act: -0.1700
Data Index: 8762162 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4115. Min Range: -9.4115
Max Act: 8.4740. Min Act: -0.1700
Data Index: 5058215 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4115. Min Range: -9.4115
Max Act: 8.4115. Min Act: -0.1700
Data Index: 563139 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4115. Min Range: -9.4115
Max Act: 8.4115. Min Act: -0.1700
Data Index: 6184572 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4115. Min Range: -9.4115
Max Act: 8.3490. Min Act: -0.1700
Data Index: 4094399 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4115. Min Range: -9.4115
Max Act: 8.2865. Min Act: -0.1700
Data Index: 3078563 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4115. Min Range: -9.4115
Max Act: 8.2240. Min Act: -0.1700
Data Index: 4515348 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4115. Min Range: -9.4115
Max Act: 8.2240. Min Act: -0.1700
Data Index: 7925818 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4115. Min Range: -9.4115
Max Act: 8.2240. Min Act: -0.1700
Data Index: 7015928 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4115. Min Range: -9.4115
Max Act: 8.2240. Min Act: -0.1700
Data Index: 2815316 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4115. Min Range: -9.4115
Max Act: 8.2240. Min Act: -0.1700
Data Index: 3505001 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4115. Min Range: -9.4115
Max Act: 8.2240. Min Act: -0.1700
Data Index: 5829617 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4115. Min Range: -9.4115
Max Act: 8.1615. Min Act: -0.1700
Data Index: 660034 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19