Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3983 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.9005. Min Act: -0.0001
Data Index: 521507 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.8146. Min Act: -0.0001
Data Index: 544057 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.6406. Min Act: -0.0001
Data Index: 386089 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.7301. Min Act: -0.0001
Data Index: 124527 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.6289. Min Act: -0.0001
Data Index: 861496 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.8030. Min Act: -0.0001
Data Index: 565190 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.7745. Min Act: -0.0001
Data Index: 629385 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.5831. Min Act: -0.0001
Data Index: 896454 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.6694. Min Act: -0.0001
Data Index: 812959 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.7528. Min Act: -0.0001
Data Index: 584160 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.6535. Min Act: -0.0001
Data Index: 936508 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.4664. Min Act: -0.0001
Data Index: 414118 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.5401. Min Act: -0.0001
Data Index: 400585 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.6811. Min Act: -0.0001
Data Index: 421576 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.6899. Min Act: -0.0001
Data Index: 354171 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.5204. Min Act: -0.0001
Data Index: 21788 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.6493. Min Act: -0.0001
Data Index: 793475 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.6424. Min Act: -0.0001
Data Index: 1281153 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.5636. Min Act: -0.0001
Data Index: 752582 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9005. Min Range: -1.9005
Max Act: 1.5647. Min Act: -0.0001
Data Index: 1280398 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19