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

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

Neuron 23 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.8953. Min Act: -0.0000

Data Index: 221814 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.8116. Min Act: -0.0000

Data Index: 839089 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.8495. Min Act: -0.0000

Data Index: 993348 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.8263. Min Act: -0.0000

Data Index: 599053 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.7549. Min Act: -0.0000

Data Index: 177855 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.8040. Min Act: -0.0000

Data Index: 1205666 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.8236. Min Act: -0.0000

Data Index: 1084383 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.7425. Min Act: -0.0000

Data Index: 272740 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.8184. Min Act: -0.0000

Data Index: 981584 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.7129. Min Act: -0.0000

Data Index: 943551 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.7199. Min Act: -0.0000

Data Index: 1319676 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.7145. Min Act: -0.0000

Data Index: 568958 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.6396. Min Act: -0.0000

Data Index: 580760 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.6991. Min Act: -0.0000

Data Index: 497858 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.7101. Min Act: -0.0000

Data Index: 15796 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.6592. Min Act: -0.0000

Data Index: 410897 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.6576. Min Act: -0.0000

Data Index: 61513 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.6974. Min Act: -0.0000

Data Index: 510540 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.6292. Min Act: -0.0000

Data Index: 212984 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 0.8953. Min Range: -0.8953

Max Act: 0.5862. Min Act: -0.0000

Data Index: 450186 (C4 (Web Text))

Max Activating Token Index: 149