Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4352 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8196. Min Range: -2.8196

Max Act: 2.6471. Min Act: -0.0000

Data Index: 251429 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 2.8196. Min Range: -2.8196

Max Act: 2.8196. Min Act: -0.0000

Data Index: 110598 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 2.8196. Min Range: -2.8196

Max Act: 2.5885. Min Act: -0.0000

Data Index: 890289 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 2.8196. Min Range: -2.8196

Max Act: 2.2780. Min Act: -0.0000

Data Index: 717550 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 2.8196. Min Range: -2.8196

Max Act: 1.9310. Min Act: -0.0000

Data Index: 217942 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 2.8196. Min Range: -2.8196

Max Act: 2.0048. Min Act: -0.0000

Data Index: 938116 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 2.8196. Min Range: -2.8196

Max Act: 2.0379. Min Act: -0.0000

Data Index: 1135252 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 2.8196. Min Range: -2.8196

Max Act: 1.7190. Min Act: -0.0000

Data Index: 850949 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 2.8196. Min Range: -2.8196

Max Act: 1.6785. Min Act: -0.0000

Data Index: 544567 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 2.8196. Min Range: -2.8196

Max Act: 1.9818. Min Act: -0.0000

Data Index: 55182 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 2.8196. Min Range: -2.8196

Max Act: 1.7022. Min Act: -0.0000

Data Index: 67283 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 2.8196. Min Range: -2.8196

Max Act: 1.7902. Min Act: -0.0000

Data Index: 1302848 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 2.8196. Min Range: -2.8196

Max Act: 1.7462. Min Act: -0.0000

Data Index: 128371 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 2.8196. Min Range: -2.8196

Max Act: 1.6430. Min Act: -0.0000

Data Index: 882453 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 2.8196. Min Range: -2.8196

Max Act: 1.7489. Min Act: -0.0000

Data Index: 421560 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 2.8196. Min Range: -2.8196

Max Act: 1.7132. Min Act: -0.0000

Data Index: 1200099 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 2.8196. Min Range: -2.8196

Max Act: 1.6082. Min Act: -0.0000

Data Index: 198456 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 2.8196. Min Range: -2.8196

Max Act: 1.6069. Min Act: -0.0000

Data Index: 1187795 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 2.8196. Min Range: -2.8196

Max Act: 1.5945. Min Act: -0.0000

Data Index: 1255891 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 2.8196. Min Range: -2.8196

Max Act: 1.4376. Min Act: -0.0000

Data Index: 684520 (C4 (Web Text))

Max Activating Token Index: 365