Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1159 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.2652. Min Range: -4.2652
Max Act: 4.2652. Min Act: -0.1700
Data Index: 272277 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2652. Min Range: -4.2652
Max Act: 4.1715. Min Act: -0.1699
Data Index: 1214907 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2652. Min Range: -4.2652
Max Act: 4.2184. Min Act: -0.1700
Data Index: 596005 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2652. Min Range: -4.2652
Max Act: 4.1558. Min Act: -0.1700
Data Index: 306831 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2652. Min Range: -4.2652
Max Act: 4.0152. Min Act: -0.1700
Data Index: 943411 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2652. Min Range: -4.2652
Max Act: 4.1246. Min Act: -0.1700
Data Index: 561009 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2652. Min Range: -4.2652
Max Act: 4.0308. Min Act: -0.1700
Data Index: 261350 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2652. Min Range: -4.2652
Max Act: 4.0152. Min Act: -0.1700
Data Index: 638452 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2652. Min Range: -4.2652
Max Act: 4.1090. Min Act: -0.1700
Data Index: 84999 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2652. Min Range: -4.2652
Max Act: 3.9995. Min Act: -0.1700
Data Index: 1300184 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2652. Min Range: -4.2652
Max Act: 4.0308. Min Act: -0.1700
Data Index: 340985 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2652. Min Range: -4.2652
Max Act: 4.0152. Min Act: -0.1697
Data Index: 763551 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2652. Min Range: -4.2652
Max Act: 3.9839. Min Act: -0.1700
Data Index: 273118 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2652. Min Range: -4.2652
Max Act: 3.9995. Min Act: -0.1700
Data Index: 1268527 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2652. Min Range: -4.2652
Max Act: 3.9526. Min Act: -0.1700
Data Index: 906507 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2652. Min Range: -4.2652
Max Act: 3.9839. Min Act: -0.1699
Data Index: 847096 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2652. Min Range: -4.2652
Max Act: 3.9526. Min Act: -0.1700
Data Index: 97965 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2652. Min Range: -4.2652
Max Act: 3.9370. Min Act: -0.1700
Data Index: 975629 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2652. Min Range: -4.2652
Max Act: 3.9526. Min Act: -0.1700
Data Index: 794572 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2652. Min Range: -4.2652
Max Act: 3.9683. Min Act: -0.1700
Data Index: 246522 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19