Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2024 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.2530. Min Range: -1.2530
Max Act: 1.2530. Min Act: -0.0001
Data Index: 1173047 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2530. Min Range: -1.2530
Max Act: 1.2082. Min Act: -0.0001
Data Index: 992612 (C4 (Web Text))
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2530. Min Range: -1.2530
Max Act: 1.1399. Min Act: -0.0001
Data Index: 694476 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2530. Min Range: -1.2530
Max Act: 1.1364. Min Act: -0.0001
Data Index: 524210 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2530. Min Range: -1.2530
Max Act: 1.1370. Min Act: -0.0001
Data Index: 416845 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2530. Min Range: -1.2530
Max Act: 1.0914. Min Act: -0.0001
Data Index: 1058852 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2530. Min Range: -1.2530
Max Act: 1.1645. Min Act: -0.0001
Data Index: 28133 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2530. Min Range: -1.2530
Max Act: 1.1592. Min Act: -0.0001
Data Index: 513552 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2530. Min Range: -1.2530
Max Act: 1.2267. Min Act: -0.0001
Data Index: 672687 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2530. Min Range: -1.2530
Max Act: 1.0953. Min Act: -0.0001
Data Index: 286016 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2530. Min Range: -1.2530
Max Act: 1.0556. Min Act: -0.0001
Data Index: 876946 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2530. Min Range: -1.2530
Max Act: 1.0212. Min Act: -0.0001
Data Index: 1310434 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2530. Min Range: -1.2530
Max Act: 1.0197. Min Act: -0.0001
Data Index: 652979 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2530. Min Range: -1.2530
Max Act: 1.0087. Min Act: -0.0001
Data Index: 127006 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2530. Min Range: -1.2530
Max Act: 0.9855. Min Act: -0.0001
Data Index: 1040954 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2530. Min Range: -1.2530
Max Act: 0.9563. Min Act: -0.0001
Data Index: 68667 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2530. Min Range: -1.2530
Max Act: 1.0130. Min Act: -0.0001
Data Index: 930454 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2530. Min Range: -1.2530
Max Act: 0.9825. Min Act: -0.0001
Data Index: 384120 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2530. Min Range: -1.2530
Max Act: 0.8757. Min Act: -0.0001
Data Index: 1581228 (Python Code)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2530. Min Range: -1.2530
Max Act: 0.8546. Min Act: -0.0001
Data Index: 398633 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19