Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4667 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0099. Min Range: -6.0099
Max Act: 6.0099. Min Act: -0.1700
Data Index: 4793236 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0099. Min Range: -6.0099
Max Act: 6.0099. Min Act: -0.1700
Data Index: 8318607 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0099. Min Range: -6.0099
Max Act: 6.0099. Min Act: -0.1700
Data Index: 7547389 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0099. Min Range: -6.0099
Max Act: 5.9474. Min Act: -0.1700
Data Index: 4524343 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0099. Min Range: -6.0099
Max Act: 5.9162. Min Act: -0.1700
Data Index: 4453805 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0099. Min Range: -6.0099
Max Act: 5.8849. Min Act: -0.1700
Data Index: 4676996 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0099. Min Range: -6.0099
Max Act: 5.8849. Min Act: -0.1700
Data Index: 6632400 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0099. Min Range: -6.0099
Max Act: 5.8537. Min Act: -0.1700
Data Index: 6701202 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0099. Min Range: -6.0099
Max Act: 5.8537. Min Act: -0.1700
Data Index: 3112127 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0099. Min Range: -6.0099
Max Act: 5.8224. Min Act: -0.1700
Data Index: 1143479 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0099. Min Range: -6.0099
Max Act: 5.8224. Min Act: -0.1700
Data Index: 3293512 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0099. Min Range: -6.0099
Max Act: 5.8224. Min Act: -0.1700
Data Index: 5965624 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0099. Min Range: -6.0099
Max Act: 5.7912. Min Act: -0.1700
Data Index: 6040321 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0099. Min Range: -6.0099
Max Act: 5.7912. Min Act: -0.1700
Data Index: 1246443 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0099. Min Range: -6.0099
Max Act: 5.7912. Min Act: -0.1700
Data Index: 8420719 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0099. Min Range: -6.0099
Max Act: 5.7912. Min Act: -0.1700
Data Index: 4980662 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0099. Min Range: -6.0099
Max Act: 5.7912. Min Act: -0.1700
Data Index: 214076 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0099. Min Range: -6.0099
Max Act: 5.7599. Min Act: -0.1700
Data Index: 1219774 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0099. Min Range: -6.0099
Max Act: 5.7599. Min Act: -0.1700
Data Index: 3770068 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0099. Min Range: -6.0099
Max Act: 5.7599. Min Act: -0.1700
Data Index: 4507406 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19