Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 113 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.7692. Min Range: -4.7692
Max Act: 4.7692. Min Act: -0.1700
Data Index: 622858 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7692. Min Range: -4.7692
Max Act: 4.6754. Min Act: -0.1698
Data Index: 776071 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7692. Min Range: -4.7692
Max Act: 4.5817. Min Act: -0.1700
Data Index: 1171639 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7692. Min Range: -4.7692
Max Act: 4.5504. Min Act: -0.1700
Data Index: 1303081 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7692. Min Range: -4.7692
Max Act: 4.5192. Min Act: -0.1699
Data Index: 701446 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7692. Min Range: -4.7692
Max Act: 4.5817. Min Act: -0.1700
Data Index: 430813 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7692. Min Range: -4.7692
Max Act: 4.5192. Min Act: -0.1700
Data Index: 620765 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7692. Min Range: -4.7692
Max Act: 4.4879. Min Act: -0.1700
Data Index: 433414 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7692. Min Range: -4.7692
Max Act: 4.5192. Min Act: -0.1700
Data Index: 164054 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7692. Min Range: -4.7692
Max Act: 4.4879. Min Act: -0.1700
Data Index: 942398 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7692. Min Range: -4.7692
Max Act: 4.4567. Min Act: -0.1700
Data Index: 458087 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7692. Min Range: -4.7692
Max Act: 4.4879. Min Act: -0.1700
Data Index: 55926 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7692. Min Range: -4.7692
Max Act: 4.4567. Min Act: -0.1700
Data Index: 15445 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7692. Min Range: -4.7692
Max Act: 4.4254. Min Act: -0.1700
Data Index: 1272324 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7692. Min Range: -4.7692
Max Act: 4.4567. Min Act: -0.1700
Data Index: 1282359 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7692. Min Range: -4.7692
Max Act: 4.4567. Min Act: -0.1699
Data Index: 739005 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7692. Min Range: -4.7692
Max Act: 4.4254. Min Act: -0.1700
Data Index: 956028 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7692. Min Range: -4.7692
Max Act: 4.3942. Min Act: -0.1699
Data Index: 95704 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7692. Min Range: -4.7692
Max Act: 4.3942. Min Act: -0.1699
Data Index: 1117375 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7692. Min Range: -4.7692
Max Act: 4.4254. Min Act: -0.1700
Data Index: 717945 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19