Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2578 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0172. Min Act: -0.0003

Data Index: 583788 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0164. Min Act: -0.0004

Data Index: 952792 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0163. Min Act: -0.0004

Data Index: 768864 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0162. Min Act: -0.0003

Data Index: 189685 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0160. Min Act: -0.0003

Data Index: 148502 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0157. Min Act: -0.0003

Data Index: 243186 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0153. Min Act: -0.0004

Data Index: 1291448 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0153. Min Act: -0.0003

Data Index: 1127844 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0152. Min Act: -0.0004

Data Index: 775593 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0152. Min Act: -0.0003

Data Index: 1127033 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0148. Min Act: -0.0003

Data Index: 523805 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0154. Min Act: -0.0004

Data Index: 608099 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0151. Min Act: -0.0003

Data Index: 745483 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0147. Min Act: -0.0003

Data Index: 922761 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0148. Min Act: -0.0003

Data Index: 1327515 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0144. Min Act: -0.0003

Data Index: 1229871 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0145. Min Act: -0.0003

Data Index: 248490 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0143. Min Act: -0.0004

Data Index: 893404 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0145. Min Act: -0.0003

Data Index: 632374 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0139. Min Act: -0.0004

Data Index: 430359 (C4 (Web Text))

Max Activating Token Index: 547