Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1967 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9762. Min Range: -2.9762
Max Act: 2.9762. Min Act: -0.1700
Data Index: 639067 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9762. Min Range: -2.9762
Max Act: 2.9762. Min Act: -0.1700
Data Index: 920351 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9762. Min Range: -2.9762
Max Act: 2.9445. Min Act: -0.1700
Data Index: 327127 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9762. Min Range: -2.9762
Max Act: 2.9603. Min Act: -0.1700
Data Index: 636893 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9762. Min Range: -2.9762
Max Act: 2.9287. Min Act: -0.1700
Data Index: 592337 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9762. Min Range: -2.9762
Max Act: 2.9287. Min Act: -0.1700
Data Index: 507335 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9762. Min Range: -2.9762
Max Act: 2.8969. Min Act: -0.1700
Data Index: 842244 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9762. Min Range: -2.9762
Max Act: 2.8652. Min Act: -0.1700
Data Index: 146478 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9762. Min Range: -2.9762
Max Act: 2.8811. Min Act: -0.1700
Data Index: 897350 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9762. Min Range: -2.9762
Max Act: 2.8652. Min Act: -0.1700
Data Index: 484246 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9762. Min Range: -2.9762
Max Act: 2.8334. Min Act: -0.1700
Data Index: 949902 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9762. Min Range: -2.9762
Max Act: 2.8334. Min Act: -0.1700
Data Index: 319342 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9762. Min Range: -2.9762
Max Act: 2.8334. Min Act: -0.1700
Data Index: 355871 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9762. Min Range: -2.9762
Max Act: 2.8334. Min Act: -0.1700
Data Index: 868269 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9762. Min Range: -2.9762
Max Act: 2.8175. Min Act: -0.1700
Data Index: 447152 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9762. Min Range: -2.9762
Max Act: 2.8334. Min Act: -0.1700
Data Index: 1201534 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9762. Min Range: -2.9762
Max Act: 2.8334. Min Act: -0.1700
Data Index: 47730 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9762. Min Range: -2.9762
Max Act: 2.8175. Min Act: -0.1700
Data Index: 607480 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9762. Min Range: -2.9762
Max Act: 2.8175. Min Act: -0.1700
Data Index: 837153 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9762. Min Range: -2.9762
Max Act: 2.8334. Min Act: -0.1700
Data Index: 43667 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19