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

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

Neuron 4083 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: 0.9250. Min Range: -0.9250

Max Act: 0.9250. Min Act: -0.0000

Data Index: 38492 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.8197. Min Act: -0.0000

Data Index: 623591 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.7713. Min Act: -0.0000

Data Index: 1071632 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.7013. Min Act: -0.0000

Data Index: 20624 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.7223. Min Act: -0.0000

Data Index: 15677 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6994. Min Act: -0.0000

Data Index: 1146000 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6551. Min Act: -0.0000

Data Index: 684175 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6277. Min Act: -0.0000

Data Index: 812498 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6670. Min Act: -0.0000

Data Index: 321963 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6594. Min Act: -0.0000

Data Index: 374362 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6524. Min Act: -0.0000

Data Index: 814672 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6399. Min Act: -0.0000

Data Index: 255705 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6413. Min Act: -0.0000

Data Index: 1173156 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6326. Min Act: -0.0000

Data Index: 182466 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6551. Min Act: -0.0000

Data Index: 656829 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6142. Min Act: -0.0000

Data Index: 1017736 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1196591 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6452. Min Act: -0.0000

Data Index: 1289855 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6260. Min Act: -0.0000

Data Index: 472878 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1231730 (C4 (Web Text))

Max Activating Token Index: 296