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

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

Neuron 3718 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0312. Min Range: -1.0312

Max Act: 1.0312. Min Act: -0.0001

Data Index: 545521 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.8477. Min Act: -0.0001

Data Index: 1416182 (Python Code)

Max Activating Token Index: 886

Text #2

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.9829. Min Act: -0.0001

Data Index: 892111 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.9429. Min Act: -0.0001

Data Index: 1467643 (Python Code)

Max Activating Token Index: 207

Text #4

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.8197. Min Act: -0.0001

Data Index: 455720 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.9464. Min Act: -0.0001

Data Index: 652956 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.8644. Min Act: -0.0001

Data Index: 1230771 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.7993. Min Act: -0.0001

Data Index: 777268 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.8705. Min Act: -0.0001

Data Index: 43611 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.8266. Min Act: -0.0001

Data Index: 428275 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.9260. Min Act: -0.0001

Data Index: 348216 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.7999. Min Act: -0.0001

Data Index: 916406 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.8443. Min Act: -0.0001

Data Index: 1546754 (Python Code)

Max Activating Token Index: 318

Text #13

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.8958. Min Act: -0.0001

Data Index: 1012711 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.7564. Min Act: -0.0001

Data Index: 1391909 (Python Code)

Max Activating Token Index: 601

Text #15

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.7546. Min Act: -0.0001

Data Index: 1415187 (Python Code)

Max Activating Token Index: 623

Text #16

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.8524. Min Act: -0.0001

Data Index: 280703 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.7476. Min Act: -0.0001

Data Index: 75533 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.7153. Min Act: -0.0001

Data Index: 1598665 (Python Code)

Max Activating Token Index: 488

Text #19

Max Range: 1.0312. Min Range: -1.0312

Max Act: 0.7811. Min Act: -0.0001

Data Index: 1070599 (C4 (Web Text))

Max Activating Token Index: 342