Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 149 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 1.9731. Min Range: -1.9731
Max Act: 1.9562. Min Act: -0.1700
Data Index: 180525 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9731. Min Range: -1.9731
Max Act: 1.9731. Min Act: -0.1700
Data Index: 63244 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9731. Min Range: -1.9731
Max Act: 1.9731. Min Act: -0.1700
Data Index: 749657 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9731. Min Range: -1.9731
Max Act: 1.9731. Min Act: -0.1700
Data Index: 605459 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9731. Min Range: -1.9731
Max Act: 1.9731. Min Act: -0.1700
Data Index: 180836 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9731. Min Range: -1.9731
Max Act: 1.9731. Min Act: -0.1700
Data Index: 743042 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9731. Min Range: -1.9731
Max Act: 1.9222. Min Act: -0.1700
Data Index: 355767 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9731. Min Range: -1.9731
Max Act: 1.9222. Min Act: -0.1700
Data Index: 1340634 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9731. Min Range: -1.9731
Max Act: 1.9222. Min Act: -0.1700
Data Index: 1009110 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9731. Min Range: -1.9731
Max Act: 1.9392. Min Act: -0.1700
Data Index: 1297740 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9731. Min Range: -1.9731
Max Act: 1.9222. Min Act: -0.1700
Data Index: 1173889 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9731. Min Range: -1.9731
Max Act: 1.9222. Min Act: -0.1700
Data Index: 1231412 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9731. Min Range: -1.9731
Max Act: 1.9222. Min Act: -0.1700
Data Index: 1487827 (Python Code)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9731. Min Range: -1.9731
Max Act: 1.9052. Min Act: -0.1700
Data Index: 951150 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9731. Min Range: -1.9731
Max Act: 1.9052. Min Act: -0.1700
Data Index: 551660 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9731. Min Range: -1.9731
Max Act: 1.9052. Min Act: -0.1700
Data Index: 575121 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9731. Min Range: -1.9731
Max Act: 1.9052. Min Act: -0.1700
Data Index: 1122054 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9731. Min Range: -1.9731
Max Act: 1.9052. Min Act: -0.1700
Data Index: 450473 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9731. Min Range: -1.9731
Max Act: 1.9052. Min Act: -0.1700
Data Index: 88635 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9731. Min Range: -1.9731
Max Act: 1.9052. Min Act: -0.1700
Data Index: 581673 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19