Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2018 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4496. Min Range: -2.4496
Max Act: 2.4496. Min Act: -0.1700
Data Index: 1052369 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4496. Min Range: -2.4496
Max Act: 2.3844. Min Act: -0.1700
Data Index: 439892 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4496. Min Range: -2.4496
Max Act: 2.3844. Min Act: -0.1700
Data Index: 635442 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4496. Min Range: -2.4496
Max Act: 2.3681. Min Act: -0.1700
Data Index: 607838 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4496. Min Range: -2.4496
Max Act: 2.3517. Min Act: -0.1700
Data Index: 1154560 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4496. Min Range: -2.4496
Max Act: 2.3681. Min Act: -0.1700
Data Index: 1116090 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4496. Min Range: -2.4496
Max Act: 2.3681. Min Act: -0.1700
Data Index: 701791 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4496. Min Range: -2.4496
Max Act: 2.3681. Min Act: -0.1700
Data Index: 1310979 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4496. Min Range: -2.4496
Max Act: 2.3681. Min Act: -0.1700
Data Index: 595044 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4496. Min Range: -2.4496
Max Act: 2.3517. Min Act: -0.1700
Data Index: 523784 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4496. Min Range: -2.4496
Max Act: 2.3517. Min Act: -0.1700
Data Index: 1163910 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4496. Min Range: -2.4496
Max Act: 2.3517. Min Act: -0.1700
Data Index: 1145278 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4496. Min Range: -2.4496
Max Act: 2.3353. Min Act: -0.1700
Data Index: 1075008 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4496. Min Range: -2.4496
Max Act: 2.3353. Min Act: -0.1700
Data Index: 1089339 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4496. Min Range: -2.4496
Max Act: 2.3353. Min Act: -0.1700
Data Index: 428019 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4496. Min Range: -2.4496
Max Act: 2.3353. Min Act: -0.1700
Data Index: 913893 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4496. Min Range: -2.4496
Max Act: 2.3353. Min Act: -0.1700
Data Index: 713674 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4496. Min Range: -2.4496
Max Act: 2.3517. Min Act: -0.1700
Data Index: 475776 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4496. Min Range: -2.4496
Max Act: 2.3353. Min Act: -0.1700
Data Index: 732954 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4496. Min Range: -2.4496
Max Act: 2.3353. Min Act: -0.1700
Data Index: 1227456 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19