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

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

Neuron 905 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.3522. Min Act: -0.0001

Data Index: 681863 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.1274. Min Act: -0.0001

Data Index: 91924 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.0977. Min Act: -0.0001

Data Index: 169009 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.0830. Min Act: -0.0001

Data Index: 38448 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9415. Min Act: -0.0001

Data Index: 561696 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.0175. Min Act: -0.0002

Data Index: 1346308 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.0093. Min Act: -0.0001

Data Index: 731784 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.0156. Min Act: -0.0001

Data Index: 818278 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9494. Min Act: -0.0002

Data Index: 648348 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 1.3522. Min Range: -1.3522

Max Act: 1.0183. Min Act: -0.0002

Data Index: 569463 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9902. Min Act: -0.0001

Data Index: 382655 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9756. Min Act: -0.0002

Data Index: 885348 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9303. Min Act: -0.0001

Data Index: 770104 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9289. Min Act: -0.0001

Data Index: 469627 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9187. Min Act: -0.0002

Data Index: 440251 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9256. Min Act: -0.0001

Data Index: 461944 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.8933. Min Act: -0.0001

Data Index: 357066 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9190. Min Act: -0.0001

Data Index: 837448 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.8143. Min Act: -0.0002

Data Index: 1315117 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 1.3522. Min Range: -1.3522

Max Act: 0.9653. Min Act: -0.0002

Data Index: 528482 (C4 (Web Text))

Max Activating Token Index: 971