Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 757 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.5866. Min Range: -2.5866
Max Act: 2.5866. Min Act: -0.1700
Data Index: 766993 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5866. Min Range: -2.5866
Max Act: 2.5704. Min Act: -0.1700
Data Index: 693515 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5866. Min Range: -2.5866
Max Act: 2.5543. Min Act: -0.1700
Data Index: 975808 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5866. Min Range: -2.5866
Max Act: 2.5543. Min Act: -0.1700
Data Index: 762021 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5866. Min Range: -2.5866
Max Act: 2.5382. Min Act: -0.1700
Data Index: 334573 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5866. Min Range: -2.5866
Max Act: 2.5382. Min Act: -0.1700
Data Index: 1240264 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5866. Min Range: -2.5866
Max Act: 2.5382. Min Act: -0.1700
Data Index: 1003044 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5866. Min Range: -2.5866
Max Act: 2.5382. Min Act: -0.1700
Data Index: 669896 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5866. Min Range: -2.5866
Max Act: 2.5220. Min Act: -0.1700
Data Index: 73427 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5866. Min Range: -2.5866
Max Act: 2.5220. Min Act: -0.1700
Data Index: 629538 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5866. Min Range: -2.5866
Max Act: 2.5058. Min Act: -0.1700
Data Index: 294580 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5866. Min Range: -2.5866
Max Act: 2.5058. Min Act: -0.1700
Data Index: 402506 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5866. Min Range: -2.5866
Max Act: 2.4896. Min Act: -0.1700
Data Index: 292163 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5866. Min Range: -2.5866
Max Act: 2.4896. Min Act: -0.1700
Data Index: 702326 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5866. Min Range: -2.5866
Max Act: 2.5058. Min Act: -0.1700
Data Index: 324779 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5866. Min Range: -2.5866
Max Act: 2.4734. Min Act: -0.1700
Data Index: 739861 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5866. Min Range: -2.5866
Max Act: 2.4734. Min Act: -0.1700
Data Index: 655185 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5866. Min Range: -2.5866
Max Act: 2.4734. Min Act: -0.1700
Data Index: 555958 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5866. Min Range: -2.5866
Max Act: 2.4734. Min Act: -0.1700
Data Index: 592476 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5866. Min Range: -2.5866
Max Act: 2.4572. Min Act: -0.1700
Data Index: 627961 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19