Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 94 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.0859. Min Range: -2.0859
Max Act: 2.0859. Min Act: -0.1700
Data Index: 255723 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0859. Min Range: -2.0859
Max Act: 2.0019. Min Act: -0.1700
Data Index: 69653 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0859. Min Range: -2.0859
Max Act: 1.9511. Min Act: -0.1700
Data Index: 410530 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0859. Min Range: -2.0859
Max Act: 1.9511. Min Act: -0.1700
Data Index: 187524 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0859. Min Range: -2.0859
Max Act: 1.9341. Min Act: -0.1700
Data Index: 819433 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0859. Min Range: -2.0859
Max Act: 1.9341. Min Act: -0.1700
Data Index: 496697 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0859. Min Range: -2.0859
Max Act: 1.9171. Min Act: -0.1700
Data Index: 688071 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0859. Min Range: -2.0859
Max Act: 1.9171. Min Act: -0.1700
Data Index: 69382 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0859. Min Range: -2.0859
Max Act: 1.9171. Min Act: -0.1700
Data Index: 1100361 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0859. Min Range: -2.0859
Max Act: 1.9001. Min Act: -0.1700
Data Index: 622409 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0859. Min Range: -2.0859
Max Act: 1.9001. Min Act: -0.1700
Data Index: 667663 (C4 (Web Text))
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0859. Min Range: -2.0859
Max Act: 1.9171. Min Act: -0.1700
Data Index: 607956 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0859. Min Range: -2.0859
Max Act: 1.9001. Min Act: -0.1700
Data Index: 577907 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0859. Min Range: -2.0859
Max Act: 1.8830. Min Act: -0.1700
Data Index: 705232 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0859. Min Range: -2.0859
Max Act: 1.9001. Min Act: -0.1700
Data Index: 744971 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0859. Min Range: -2.0859
Max Act: 1.8830. Min Act: -0.1700
Data Index: 958261 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0859. Min Range: -2.0859
Max Act: 1.8830. Min Act: -0.1700
Data Index: 164507 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0859. Min Range: -2.0859
Max Act: 1.8830. Min Act: -0.1700
Data Index: 521334 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0859. Min Range: -2.0859
Max Act: 1.8659. Min Act: -0.1700
Data Index: 706774 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0859. Min Range: -2.0859
Max Act: 1.8659. Min Act: -0.1700
Data Index: 36643 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19