Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6384 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6511. Min Range: -10.6511
Max Act: 10.6511. Min Act: -0.1700
Data Index: 6781582 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6511. Min Range: -10.6511
Max Act: 10.3386. Min Act: -0.1700
Data Index: 4491365 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6511. Min Range: -10.6511
Max Act: 10.3386. Min Act: -0.1700
Data Index: 8785742 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6511. Min Range: -10.6511
Max Act: 10.1511. Min Act: -0.1700
Data Index: 4737182 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6511. Min Range: -10.6511
Max Act: 10.0261. Min Act: -0.1700
Data Index: 264585 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6511. Min Range: -10.6511
Max Act: 10.0261. Min Act: -0.1700
Data Index: 7637092 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6511. Min Range: -10.6511
Max Act: 9.9636. Min Act: -0.1700
Data Index: 4904696 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6511. Min Range: -10.6511
Max Act: 9.9011. Min Act: -0.1700
Data Index: 7137496 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6511. Min Range: -10.6511
Max Act: 9.9636. Min Act: -0.1700
Data Index: 2018390 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6511. Min Range: -10.6511
Max Act: 9.9636. Min Act: -0.1700
Data Index: 5962063 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6511. Min Range: -10.6511
Max Act: 9.9011. Min Act: -0.1700
Data Index: 3736322 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6511. Min Range: -10.6511
Max Act: 9.7761. Min Act: -0.1700
Data Index: 7892039 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6511. Min Range: -10.6511
Max Act: 9.7761. Min Act: -0.1700
Data Index: 7024058 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6511. Min Range: -10.6511
Max Act: 9.7761. Min Act: -0.1700
Data Index: 6866530 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6511. Min Range: -10.6511
Max Act: 9.7136. Min Act: -0.1700
Data Index: 6160779 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6511. Min Range: -10.6511
Max Act: 9.7761. Min Act: -0.1700
Data Index: 7667867 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6511. Min Range: -10.6511
Max Act: 9.6511. Min Act: -0.1700
Data Index: 6898498 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6511. Min Range: -10.6511
Max Act: 9.7136. Min Act: -0.1700
Data Index: 1476684 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6511. Min Range: -10.6511
Max Act: 9.7136. Min Act: -0.1700
Data Index: 3621030 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6511. Min Range: -10.6511
Max Act: 9.6511. Min Act: -0.1700
Data Index: 6930722 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19