Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1747 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.4099. Min Range: -4.4099
Max Act: 4.3474. Min Act: -0.1700
Data Index: 422451 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4099. Min Range: -4.4099
Max Act: 4.4099. Min Act: -0.1700
Data Index: 717780 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4099. Min Range: -4.4099
Max Act: 4.3474. Min Act: -0.1700
Data Index: 394532 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4099. Min Range: -4.4099
Max Act: 4.4099. Min Act: -0.1700
Data Index: 306399 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4099. Min Range: -4.4099
Max Act: 4.3474. Min Act: -0.1700
Data Index: 48783 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4099. Min Range: -4.4099
Max Act: 4.2849. Min Act: -0.1700
Data Index: 1095114 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4099. Min Range: -4.4099
Max Act: 4.2537. Min Act: -0.1700
Data Index: 960655 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4099. Min Range: -4.4099
Max Act: 4.3162. Min Act: -0.1700
Data Index: 1337705 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4099. Min Range: -4.4099
Max Act: 4.2849. Min Act: -0.1700
Data Index: 958860 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4099. Min Range: -4.4099
Max Act: 4.1912. Min Act: -0.1700
Data Index: 119921 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4099. Min Range: -4.4099
Max Act: 4.3162. Min Act: -0.1700
Data Index: 564164 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4099. Min Range: -4.4099
Max Act: 4.2224. Min Act: -0.1700
Data Index: 1077226 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4099. Min Range: -4.4099
Max Act: 4.2224. Min Act: -0.1700
Data Index: 701877 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4099. Min Range: -4.4099
Max Act: 4.2224. Min Act: -0.1700
Data Index: 1124078 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4099. Min Range: -4.4099
Max Act: 4.2849. Min Act: -0.1700
Data Index: 992965 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4099. Min Range: -4.4099
Max Act: 4.1599. Min Act: -0.1700
Data Index: 1070784 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4099. Min Range: -4.4099
Max Act: 4.1286. Min Act: -0.1700
Data Index: 261506 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4099. Min Range: -4.4099
Max Act: 4.1912. Min Act: -0.1700
Data Index: 644172 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4099. Min Range: -4.4099
Max Act: 4.1912. Min Act: -0.1700
Data Index: 878515 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4099. Min Range: -4.4099
Max Act: 4.1912. Min Act: -0.1700
Data Index: 625615 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19