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

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

Neuron 2244 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.4236. Min Act: -0.0002

Data Index: 669972 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.4339. Min Act: -0.0002

Data Index: 755827 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3876. Min Act: -0.0003

Data Index: 840964 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.3203. Min Act: -0.0002

Data Index: 746311 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.2893. Min Act: -0.0003

Data Index: 169066 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.2812. Min Act: -0.0003

Data Index: 718402 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.2806. Min Act: -0.0002

Data Index: 262772 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.2568. Min Act: -0.0002

Data Index: 556754 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.2740. Min Act: -0.0003

Data Index: 62101 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.2539. Min Act: -0.0002

Data Index: 460088 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.2507. Min Act: -0.0003

Data Index: 1230580 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.2452. Min Act: -0.0003

Data Index: 400773 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.2162. Min Act: -0.0002

Data Index: 324730 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.2257. Min Act: -0.0003

Data Index: 764959 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.2236. Min Act: -0.0003

Data Index: 394682 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.2218. Min Act: -0.0002

Data Index: 101885 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.2212. Min Act: -0.0003

Data Index: 161140 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.2206. Min Act: -0.0003

Data Index: 526783 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.2206. Min Act: -0.0002

Data Index: 1279150 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.4339. Min Range: -0.4339

Max Act: 0.2184. Min Act: -0.0003

Data Index: 756507 (C4 (Web Text))

Max Activating Token Index: 10