Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1702 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.6717. Min Range: -0.6717
Max Act: 0.6717. Min Act: -0.0001
Data Index: 873904 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6717. Min Range: -0.6717
Max Act: 0.6483. Min Act: -0.0001
Data Index: 419432 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6717. Min Range: -0.6717
Max Act: 0.6093. Min Act: -0.0001
Data Index: 768813 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6717. Min Range: -0.6717
Max Act: 0.5807. Min Act: -0.0001
Data Index: 293109 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6717. Min Range: -0.6717
Max Act: 0.6184. Min Act: -0.0001
Data Index: 816329 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6717. Min Range: -0.6717
Max Act: 0.5714. Min Act: -0.0001
Data Index: 1102120 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6717. Min Range: -0.6717
Max Act: 0.5788. Min Act: -0.0001
Data Index: 483520 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6717. Min Range: -0.6717
Max Act: 0.5513. Min Act: -0.0001
Data Index: 230517 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6717. Min Range: -0.6717
Max Act: 0.5681. Min Act: -0.0001
Data Index: 1075074 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6717. Min Range: -0.6717
Max Act: 0.4643. Min Act: -0.0001
Data Index: 661814 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6717. Min Range: -0.6717
Max Act: 0.5289. Min Act: -0.0001
Data Index: 892550 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6717. Min Range: -0.6717
Max Act: 0.5445. Min Act: -0.0001
Data Index: 513557 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6717. Min Range: -0.6717
Max Act: 0.6120. Min Act: -0.0001
Data Index: 4660 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6717. Min Range: -0.6717
Max Act: 0.5345. Min Act: -0.0001
Data Index: 353495 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6717. Min Range: -0.6717
Max Act: 0.5559. Min Act: -0.0001
Data Index: 442613 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6717. Min Range: -0.6717
Max Act: 0.5351. Min Act: -0.0001
Data Index: 461511 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6717. Min Range: -0.6717
Max Act: 0.5202. Min Act: -0.0001
Data Index: 236559 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6717. Min Range: -0.6717
Max Act: 0.5201. Min Act: -0.0001
Data Index: 937464 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6717. Min Range: -0.6717
Max Act: 0.5368. Min Act: -0.0001
Data Index: 334926 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6717. Min Range: -0.6717
Max Act: 0.5682. Min Act: -0.0001
Data Index: 900452 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19