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

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

Neuron 3509 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.3099. Min Act: -0.0001

Data Index: 43931 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2741. Min Act: -0.0001

Data Index: 1088751 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2806. Min Act: -0.0001

Data Index: 583285 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2625. Min Act: -0.0001

Data Index: 113287 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2379. Min Act: -0.0001

Data Index: 1056633 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2552. Min Act: -0.0001

Data Index: 562787 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2524. Min Act: -0.0001

Data Index: 457641 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2355. Min Act: -0.0001

Data Index: 1155148 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2458. Min Act: -0.0001

Data Index: 674930 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2369. Min Act: -0.0001

Data Index: 779631 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2361. Min Act: -0.0001

Data Index: 1225289 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2207. Min Act: -0.0001

Data Index: 312315 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2462. Min Act: -0.0001

Data Index: 64983 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2123. Min Act: -0.0001

Data Index: 923299 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2311. Min Act: -0.0001

Data Index: 425766 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2307. Min Act: -0.0001

Data Index: 58618 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2206. Min Act: -0.0001

Data Index: 277659 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2208. Min Act: -0.0001

Data Index: 610447 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2283. Min Act: -0.0001

Data Index: 80220 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2124. Min Act: -0.0001

Data Index: 329195 (C4 (Web Text))

Max Activating Token Index: 812