Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 630 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0172. Min Act: -0.0006

Data Index: 871695 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0171. Min Act: -0.0006

Data Index: 451563 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0167. Min Act: -0.0006

Data Index: 108385 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0171. Min Act: -0.0006

Data Index: 374678 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0170. Min Act: -0.0006

Data Index: 1046797 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0162. Min Act: -0.0006

Data Index: 410973 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0158. Min Act: -0.0006

Data Index: 263626 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0160. Min Act: -0.0006

Data Index: 1207410 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0153. Min Act: -0.0006

Data Index: 719277 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0157. Min Act: -0.0006

Data Index: 927524 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0154. Min Act: -0.0006

Data Index: 1080613 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1290625 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0155. Min Act: -0.0006

Data Index: 374827 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0145. Min Act: -0.0006

Data Index: 858113 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1147991 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1303069 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0142. Min Act: -0.0006

Data Index: 520901 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0141. Min Act: -0.0006

Data Index: 874003 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0147. Min Act: -0.0006

Data Index: 1076567 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1266183 (C4 (Web Text))

Max Activating Token Index: 145