Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2022 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0162. Min Act: -0.0002

Data Index: 1180767 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0167. Min Act: -0.0002

Data Index: 957196 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0155. Min Act: -0.0002

Data Index: 1291864 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0161. Min Act: -0.0003

Data Index: 748278 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0156. Min Act: -0.0002

Data Index: 1270202 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0152. Min Act: -0.0002

Data Index: 742674 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0156. Min Act: -0.0003

Data Index: 455196 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1284540 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0143. Min Act: -0.0003

Data Index: 74552 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1353300 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1242940 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0142. Min Act: -0.0003

Data Index: 261374 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0136. Min Act: -0.0003

Data Index: 13056 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0131. Min Act: -0.0002

Data Index: 338215 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0131. Min Act: -0.0003

Data Index: 1006128 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0128. Min Act: -0.0002

Data Index: 509343 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0121. Min Act: -0.0003

Data Index: 98690 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0127. Min Act: -0.0002

Data Index: 661503 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0126. Min Act: -0.0003

Data Index: 342813 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0130. Min Act: -0.0003

Data Index: 180483 (C4 (Web Text))

Max Activating Token Index: 389