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

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

Neuron 2547 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.8280. Min Act: -0.0000

Data Index: 1290657 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.7565. Min Act: -0.0000

Data Index: 946442 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.6337. Min Act: -0.0000

Data Index: 730813 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.6346. Min Act: -0.0001

Data Index: 946966 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.6205. Min Act: -0.0000

Data Index: 116725 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.6572. Min Act: -0.0001

Data Index: 966454 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.6278. Min Act: -0.0000

Data Index: 445251 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.6196. Min Act: -0.0000

Data Index: 1027358 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.6371. Min Act: -0.0000

Data Index: 290869 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.6168. Min Act: -0.0000

Data Index: 517178 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.5892. Min Act: -0.0000

Data Index: 265035 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.5968. Min Act: -0.0000

Data Index: 307770 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.5908. Min Act: -0.0001

Data Index: 189171 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.5894. Min Act: -0.0000

Data Index: 966521 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.5855. Min Act: -0.0000

Data Index: 1197471 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.5805. Min Act: -0.0000

Data Index: 546919 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.5761. Min Act: -0.0000

Data Index: 360773 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.5769. Min Act: -0.0000

Data Index: 245035 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.5384. Min Act: -0.0000

Data Index: 98223 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.5570. Min Act: -0.0000

Data Index: 19480 (C4 (Web Text))

Max Activating Token Index: 169