Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2006 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.4885. Min Range: -4.4885
Max Act: 4.4885. Min Act: -0.1700
Data Index: 376337 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4885. Min Range: -4.4885
Max Act: 4.3635. Min Act: -0.1700
Data Index: 533082 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4885. Min Range: -4.4885
Max Act: 4.3948. Min Act: -0.1700
Data Index: 865270 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4885. Min Range: -4.4885
Max Act: 4.3635. Min Act: -0.1700
Data Index: 209192 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4885. Min Range: -4.4885
Max Act: 4.3323. Min Act: -0.1700
Data Index: 748486 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4885. Min Range: -4.4885
Max Act: 4.3010. Min Act: -0.1700
Data Index: 291901 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4885. Min Range: -4.4885
Max Act: 4.3323. Min Act: -0.1700
Data Index: 1028638 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4885. Min Range: -4.4885
Max Act: 4.3323. Min Act: -0.1700
Data Index: 1210524 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4885. Min Range: -4.4885
Max Act: 4.2697. Min Act: -0.1700
Data Index: 1044108 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4885. Min Range: -4.4885
Max Act: 4.1760. Min Act: -0.1700
Data Index: 259484 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4885. Min Range: -4.4885
Max Act: 4.2072. Min Act: -0.1700
Data Index: 98378 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4885. Min Range: -4.4885
Max Act: 4.2072. Min Act: -0.1700
Data Index: 872529 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4885. Min Range: -4.4885
Max Act: 4.2072. Min Act: -0.1700
Data Index: 1352262 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4885. Min Range: -4.4885
Max Act: 4.2072. Min Act: -0.1700
Data Index: 1297486 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4885. Min Range: -4.4885
Max Act: 4.1760. Min Act: -0.1700
Data Index: 711204 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4885. Min Range: -4.4885
Max Act: 4.2072. Min Act: -0.1700
Data Index: 865749 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4885. Min Range: -4.4885
Max Act: 4.1447. Min Act: -0.1700
Data Index: 162690 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4885. Min Range: -4.4885
Max Act: 4.1760. Min Act: -0.1700
Data Index: 151654 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4885. Min Range: -4.4885
Max Act: 4.1760. Min Act: -0.1700
Data Index: 151218 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4885. Min Range: -4.4885
Max Act: 4.1760. Min Act: -0.1700
Data Index: 1052620 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19