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

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

Neuron 795 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5142. Min Range: -3.5142

Max Act: 3.5142. Min Act: -0.0001

Data Index: 259631 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 3.5142. Min Range: -3.5142

Max Act: 3.3637. Min Act: -0.0001

Data Index: 1231265 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 3.5142. Min Range: -3.5142

Max Act: 3.1941. Min Act: -0.0001

Data Index: 655205 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 3.5142. Min Range: -3.5142

Max Act: 2.9779. Min Act: -0.0001

Data Index: 1203815 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 3.5142. Min Range: -3.5142

Max Act: 3.0290. Min Act: -0.0001

Data Index: 17063 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 3.5142. Min Range: -3.5142

Max Act: 3.0101. Min Act: -0.0001

Data Index: 589903 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 3.5142. Min Range: -3.5142

Max Act: 2.9787. Min Act: -0.0001

Data Index: 438695 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 3.5142. Min Range: -3.5142

Max Act: 2.9021. Min Act: -0.0001

Data Index: 1075538 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 3.5142. Min Range: -3.5142

Max Act: 2.8986. Min Act: -0.0001

Data Index: 926027 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 3.5142. Min Range: -3.5142

Max Act: 2.6954. Min Act: -0.0001

Data Index: 979639 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 3.5142. Min Range: -3.5142

Max Act: 2.6526. Min Act: -0.0001

Data Index: 1052659 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 3.5142. Min Range: -3.5142

Max Act: 2.8911. Min Act: -0.0001

Data Index: 1096406 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 3.5142. Min Range: -3.5142

Max Act: 2.7462. Min Act: -0.0001

Data Index: 1037212 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 3.5142. Min Range: -3.5142

Max Act: 2.7287. Min Act: -0.0001

Data Index: 390885 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 3.5142. Min Range: -3.5142

Max Act: 2.5864. Min Act: -0.0001

Data Index: 1259364 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 3.5142. Min Range: -3.5142

Max Act: 2.7199. Min Act: -0.0001

Data Index: 416288 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 3.5142. Min Range: -3.5142

Max Act: 2.5613. Min Act: -0.0001

Data Index: 1272904 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 3.5142. Min Range: -3.5142

Max Act: 2.6812. Min Act: -0.0001

Data Index: 849745 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 3.5142. Min Range: -3.5142

Max Act: 2.6966. Min Act: -0.0001

Data Index: 372653 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 3.5142. Min Range: -3.5142

Max Act: 2.6165. Min Act: -0.0001

Data Index: 904442 (C4 (Web Text))

Max Activating Token Index: 204