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

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

Neuron 94 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3749. Min Act: -0.0003

Data Index: 641522 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3632. Min Act: -0.0003

Data Index: 50948 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3625. Min Act: -0.0003

Data Index: 205912 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3354. Min Act: -0.0004

Data Index: 949390 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3255. Min Act: -0.0003

Data Index: 934362 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3346. Min Act: -0.0003

Data Index: 1262257 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2970. Min Act: -0.0003

Data Index: 612556 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3334. Min Act: -0.0003

Data Index: 10343 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3419. Min Act: -0.0003

Data Index: 418386 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3137. Min Act: -0.0003

Data Index: 55458 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2877. Min Act: -0.0003

Data Index: 591920 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3215. Min Act: -0.0003

Data Index: 586753 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3078. Min Act: -0.0003

Data Index: 169260 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3166. Min Act: -0.0003

Data Index: 887299 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3259. Min Act: -0.0003

Data Index: 1313855 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3027. Min Act: -0.0004

Data Index: 976087 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3127. Min Act: -0.0003

Data Index: 194820 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3118. Min Act: -0.0003

Data Index: 431565 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.3109. Min Act: -0.0003

Data Index: 238598 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.3749. Min Range: -0.3749

Max Act: 0.2991. Min Act: -0.0003

Data Index: 1078999 (C4 (Web Text))

Max Activating Token Index: 859