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

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

Neuron 2119 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2216. Min Range: -1.2216

Max Act: 1.2216. Min Act: -0.0001

Data Index: 732602 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 1.2216. Min Range: -1.2216

Max Act: 1.2138. Min Act: -0.0001

Data Index: 204246 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 1.2216. Min Range: -1.2216

Max Act: 1.0238. Min Act: -0.0001

Data Index: 887281 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 1.2216. Min Range: -1.2216

Max Act: 0.9762. Min Act: -0.0001

Data Index: 1086029 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 1.2216. Min Range: -1.2216

Max Act: 0.9124. Min Act: -0.0001

Data Index: 317413 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 1.2216. Min Range: -1.2216

Max Act: 0.8733. Min Act: -0.0001

Data Index: 827686 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 1.2216. Min Range: -1.2216

Max Act: 0.9082. Min Act: -0.0001

Data Index: 177246 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 1.2216. Min Range: -1.2216

Max Act: 0.8514. Min Act: -0.0001

Data Index: 1141326 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 1.2216. Min Range: -1.2216

Max Act: 0.8255. Min Act: -0.0001

Data Index: 1005603 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 1.2216. Min Range: -1.2216

Max Act: 0.7920. Min Act: -0.0001

Data Index: 576809 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 1.2216. Min Range: -1.2216

Max Act: 0.8427. Min Act: -0.0001

Data Index: 414181 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 1.2216. Min Range: -1.2216

Max Act: 0.7886. Min Act: -0.0001

Data Index: 487312 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 1.2216. Min Range: -1.2216

Max Act: 0.8370. Min Act: -0.0001

Data Index: 1309785 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 1.2216. Min Range: -1.2216

Max Act: 0.8070. Min Act: -0.0001

Data Index: 1281068 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 1.2216. Min Range: -1.2216

Max Act: 0.7890. Min Act: -0.0001

Data Index: 255163 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 1.2216. Min Range: -1.2216

Max Act: 0.7490. Min Act: -0.0001

Data Index: 1224536 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 1.2216. Min Range: -1.2216

Max Act: 0.7533. Min Act: -0.0001

Data Index: 1147347 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 1.2216. Min Range: -1.2216

Max Act: 0.7435. Min Act: -0.0001

Data Index: 295000 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 1.2216. Min Range: -1.2216

Max Act: 0.7382. Min Act: -0.0001

Data Index: 144241 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 1.2216. Min Range: -1.2216

Max Act: 0.7509. Min Act: -0.0001

Data Index: 1120598 (C4 (Web Text))

Max Activating Token Index: 776