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

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

Neuron 314 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9160. Min Range: -0.9160

Max Act: 0.9160. Min Act: -0.0001

Data Index: 384358 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 0.9160. Min Range: -0.9160

Max Act: 0.8473. Min Act: -0.0001

Data Index: 751022 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 0.9160. Min Range: -0.9160

Max Act: 0.8004. Min Act: -0.0001

Data Index: 1241887 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 0.9160. Min Range: -0.9160

Max Act: 0.7507. Min Act: -0.0001

Data Index: 1136193 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 0.9160. Min Range: -0.9160

Max Act: 0.7391. Min Act: -0.0001

Data Index: 800520 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.9160. Min Range: -0.9160

Max Act: 0.7345. Min Act: -0.0001

Data Index: 711066 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.9160. Min Range: -0.9160

Max Act: 0.7241. Min Act: -0.0001

Data Index: 628119 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 0.9160. Min Range: -0.9160

Max Act: 0.7202. Min Act: -0.0001

Data Index: 301786 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 0.9160. Min Range: -0.9160

Max Act: 0.7448. Min Act: -0.0001

Data Index: 638263 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 0.9160. Min Range: -0.9160

Max Act: 0.7337. Min Act: -0.0001

Data Index: 1192306 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 0.9160. Min Range: -0.9160

Max Act: 0.6885. Min Act: -0.0001

Data Index: 997173 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 0.9160. Min Range: -0.9160

Max Act: 0.7063. Min Act: -0.0001

Data Index: 833408 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.9160. Min Range: -0.9160

Max Act: 0.6859. Min Act: -0.0001

Data Index: 1194495 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 0.9160. Min Range: -0.9160

Max Act: 0.7272. Min Act: -0.0001

Data Index: 592222 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 0.9160. Min Range: -0.9160

Max Act: 0.7129. Min Act: -0.0001

Data Index: 533152 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.9160. Min Range: -0.9160

Max Act: 0.6857. Min Act: -0.0001

Data Index: 4689 (C4 (Web Text))

Max Activating Token Index: 468

Text #16

Max Range: 0.9160. Min Range: -0.9160

Max Act: 0.7003. Min Act: -0.0001

Data Index: 532328 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 0.9160. Min Range: -0.9160

Max Act: 0.7005. Min Act: -0.0001

Data Index: 771491 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 0.9160. Min Range: -0.9160

Max Act: 0.6920. Min Act: -0.0001

Data Index: 1338024 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 0.9160. Min Range: -0.9160

Max Act: 0.6691. Min Act: -0.0001

Data Index: 133070 (C4 (Web Text))

Max Activating Token Index: 590