Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1859 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.9051. Min Range: -4.9051
Max Act: 4.8739. Min Act: -0.1700
Data Index: 373522 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9051. Min Range: -4.9051
Max Act: 4.9051. Min Act: -0.1700
Data Index: 232985 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9051. Min Range: -4.9051
Max Act: 4.8739. Min Act: -0.1700
Data Index: 108179 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9051. Min Range: -4.9051
Max Act: 4.8739. Min Act: -0.1700
Data Index: 234775 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9051. Min Range: -4.9051
Max Act: 4.8114. Min Act: -0.1700
Data Index: 772873 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9051. Min Range: -4.9051
Max Act: 4.8426. Min Act: -0.1700
Data Index: 1020087 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9051. Min Range: -4.9051
Max Act: 4.8426. Min Act: -0.1700
Data Index: 1047793 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9051. Min Range: -4.9051
Max Act: 4.8426. Min Act: -0.1700
Data Index: 490690 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9051. Min Range: -4.9051
Max Act: 4.7801. Min Act: -0.1700
Data Index: 502625 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9051. Min Range: -4.9051
Max Act: 4.8426. Min Act: -0.1700
Data Index: 509699 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9051. Min Range: -4.9051
Max Act: 4.8114. Min Act: -0.1700
Data Index: 690639 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9051. Min Range: -4.9051
Max Act: 4.8114. Min Act: -0.1700
Data Index: 262595 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9051. Min Range: -4.9051
Max Act: 4.7801. Min Act: -0.1700
Data Index: 306692 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9051. Min Range: -4.9051
Max Act: 4.8114. Min Act: -0.1700
Data Index: 588436 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9051. Min Range: -4.9051
Max Act: 4.8426. Min Act: -0.1700
Data Index: 56537 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9051. Min Range: -4.9051
Max Act: 4.8114. Min Act: -0.1700
Data Index: 83369 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9051. Min Range: -4.9051
Max Act: 4.8114. Min Act: -0.1700
Data Index: 358119 (C4 (Web Text))
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9051. Min Range: -4.9051
Max Act: 4.7801. Min Act: -0.1700
Data Index: 359404 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9051. Min Range: -4.9051
Max Act: 4.7801. Min Act: -0.1700
Data Index: 45319 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9051. Min Range: -4.9051
Max Act: 4.8114. Min Act: -0.1700
Data Index: 731561 (C4 (Web Text))
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19