Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4052 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0344. Min Range: -6.0344
Max Act: 6.0344. Min Act: -0.1700
Data Index: 810025 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0344. Min Range: -6.0344
Max Act: 6.0344. Min Act: -0.1700
Data Index: 2258013 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0344. Min Range: -6.0344
Max Act: 5.9719. Min Act: -0.1700
Data Index: 2913617 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0344. Min Range: -6.0344
Max Act: 6.0032. Min Act: -0.1700
Data Index: 548622 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0344. Min Range: -6.0344
Max Act: 6.0032. Min Act: -0.1700
Data Index: 7196665 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0344. Min Range: -6.0344
Max Act: 5.9719. Min Act: -0.1700
Data Index: 2359854 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0344. Min Range: -6.0344
Max Act: 5.9719. Min Act: -0.1700
Data Index: 7518487 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0344. Min Range: -6.0344
Max Act: 5.9407. Min Act: -0.1700
Data Index: 7909454 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0344. Min Range: -6.0344
Max Act: 5.8469. Min Act: -0.1700
Data Index: 7477106 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0344. Min Range: -6.0344
Max Act: 5.8157. Min Act: -0.1700
Data Index: 7625008 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0344. Min Range: -6.0344
Max Act: 5.7844. Min Act: -0.1700
Data Index: 8789368 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0344. Min Range: -6.0344
Max Act: 5.8157. Min Act: -0.1700
Data Index: 3066529 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0344. Min Range: -6.0344
Max Act: 5.7844. Min Act: -0.1700
Data Index: 6001358 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0344. Min Range: -6.0344
Max Act: 5.7532. Min Act: -0.1700
Data Index: 835589 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0344. Min Range: -6.0344
Max Act: 5.7532. Min Act: -0.1700
Data Index: 6450735 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0344. Min Range: -6.0344
Max Act: 5.7532. Min Act: -0.1700
Data Index: 5725358 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0344. Min Range: -6.0344
Max Act: 5.7532. Min Act: -0.1700
Data Index: 1457846 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0344. Min Range: -6.0344
Max Act: 5.7532. Min Act: -0.1700
Data Index: 61546 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0344. Min Range: -6.0344
Max Act: 5.6907. Min Act: -0.1700
Data Index: 3527400 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0344. Min Range: -6.0344
Max Act: 5.7219. Min Act: -0.1700
Data Index: 2643687 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19