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

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

Neuron 497 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.3090. Min Act: -0.0000

Data Index: 649103 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.2855. Min Act: -0.0000

Data Index: 949676 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.2686. Min Act: -0.0001

Data Index: 674881 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.2744. Min Act: -0.0001

Data Index: 76687 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.2572. Min Act: -0.0000

Data Index: 737247 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.2504. Min Act: -0.0001

Data Index: 199553 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.2281. Min Act: -0.0001

Data Index: 76018 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.2519. Min Act: -0.0001

Data Index: 677259 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.2550. Min Act: -0.0001

Data Index: 865066 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.2293. Min Act: -0.0000

Data Index: 1182652 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.2322. Min Act: -0.0001

Data Index: 627333 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.2230. Min Act: -0.0000

Data Index: 716492 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.2380. Min Act: -0.0001

Data Index: 1305681 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.2301. Min Act: -0.0001

Data Index: 504028 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.2256. Min Act: -0.0001

Data Index: 267860 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.2240. Min Act: -0.0001

Data Index: 129238 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.2179. Min Act: -0.0001

Data Index: 1001370 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.2225. Min Act: -0.0001

Data Index: 295949 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.2297. Min Act: -0.0001

Data Index: 927977 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.2201. Min Act: -0.0001

Data Index: 371295 (C4 (Web Text))

Max Activating Token Index: 43