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

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

Neuron 1620 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.9348. Min Act: -0.0002

Data Index: 1068831 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.3454. Min Act: -0.0002

Data Index: 759843 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.7142. Min Act: -0.0002

Data Index: 675153 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.5358. Min Act: -0.0002

Data Index: 887560 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.4380. Min Act: -0.0002

Data Index: 666970 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.3461. Min Act: -0.0002

Data Index: 1351297 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.5367. Min Act: -0.0002

Data Index: 468498 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.3897. Min Act: -0.0002

Data Index: 430310 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.2395. Min Act: -0.0002

Data Index: 1255118 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.3325. Min Act: -0.0002

Data Index: 1326038 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.1833. Min Act: -0.0002

Data Index: 314212 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.3265. Min Act: -0.0002

Data Index: 360023 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.2602. Min Act: -0.0002

Data Index: 673745 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.2575. Min Act: -0.0002

Data Index: 1117148 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.2877. Min Act: -0.0002

Data Index: 600464 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.1812. Min Act: -0.0002

Data Index: 1112651 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.0853. Min Act: -0.0002

Data Index: 712551 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.1826. Min Act: -0.0002

Data Index: 128545 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.1593. Min Act: -0.0002

Data Index: 707691 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.0568. Min Act: -0.0002

Data Index: 755191 (C4 (Web Text))

Max Activating Token Index: 206