Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3513 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.7264. Min Act: -0.0001

Data Index: 866363 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.5652. Min Act: -0.0001

Data Index: 765516 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.6296. Min Act: -0.0001

Data Index: 814450 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.6153. Min Act: -0.0001

Data Index: 433052 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.4831. Min Act: -0.0001

Data Index: 987150 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.4093. Min Act: -0.0001

Data Index: 743973 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.5520. Min Act: -0.0001

Data Index: 225987 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.4360. Min Act: -0.0001

Data Index: 1120821 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.4373. Min Act: -0.0001

Data Index: 633354 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.3427. Min Act: -0.0001

Data Index: 732242 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.3692. Min Act: -0.0001

Data Index: 955357 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.3731. Min Act: -0.0001

Data Index: 1220469 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.3152. Min Act: -0.0001

Data Index: 906628 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.2769. Min Act: -0.0001

Data Index: 1083245 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.1924. Min Act: -0.0001

Data Index: 287825 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.2177. Min Act: -0.0001

Data Index: 1086279 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.2958. Min Act: -0.0001

Data Index: 1011554 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.2154. Min Act: -0.0001

Data Index: 794636 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.2808. Min Act: -0.0001

Data Index: 519692 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.2904. Min Act: -0.0001

Data Index: 374223 (C4 (Web Text))

Max Activating Token Index: 227