Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3244 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7411. Min Range: -1.7411

Max Act: 1.7411. Min Act: -0.0001

Data Index: 522667 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 1.7411. Min Range: -1.7411

Max Act: 1.7211. Min Act: -0.0000

Data Index: 503204 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 1.7411. Min Range: -1.7411

Max Act: 1.5208. Min Act: -0.0001

Data Index: 1121576 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 1.7411. Min Range: -1.7411

Max Act: 1.5382. Min Act: -0.0001

Data Index: 96962 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 1.7411. Min Range: -1.7411

Max Act: 1.5679. Min Act: -0.0001

Data Index: 100497 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 1.7411. Min Range: -1.7411

Max Act: 1.5259. Min Act: -0.0001

Data Index: 483179 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 1.7411. Min Range: -1.7411

Max Act: 1.4407. Min Act: -0.0000

Data Index: 917570 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 1.7411. Min Range: -1.7411

Max Act: 1.4203. Min Act: -0.0000

Data Index: 730909 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 1.7411. Min Range: -1.7411

Max Act: 1.3694. Min Act: -0.0001

Data Index: 1147473 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 1.7411. Min Range: -1.7411

Max Act: 1.3977. Min Act: -0.0000

Data Index: 1245704 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 1.7411. Min Range: -1.7411

Max Act: 1.3877. Min Act: -0.0001

Data Index: 175311 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 1.7411. Min Range: -1.7411

Max Act: 1.3893. Min Act: -0.0001

Data Index: 1100955 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 1.7411. Min Range: -1.7411

Max Act: 1.4662. Min Act: -0.0000

Data Index: 599366 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 1.7411. Min Range: -1.7411

Max Act: 1.3514. Min Act: -0.0000

Data Index: 419981 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 1.7411. Min Range: -1.7411

Max Act: 1.0209. Min Act: -0.0000

Data Index: 675167 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 1.7411. Min Range: -1.7411

Max Act: 1.3479. Min Act: -0.0000

Data Index: 118604 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 1.7411. Min Range: -1.7411

Max Act: 1.3639. Min Act: -0.0001

Data Index: 901808 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 1.7411. Min Range: -1.7411

Max Act: 1.2739. Min Act: -0.0000

Data Index: 564809 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 1.7411. Min Range: -1.7411

Max Act: 1.3236. Min Act: -0.0001

Data Index: 882473 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 1.7411. Min Range: -1.7411

Max Act: 1.3779. Min Act: -0.0000

Data Index: 871278 (C4 (Web Text))

Max Activating Token Index: 830