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

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

Neuron 1680 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0167. Min Act: -0.0004

Data Index: 144532 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0160. Min Act: -0.0004

Data Index: 24035 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0150. Min Act: -0.0004

Data Index: 456058 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0163. Min Act: -0.0004

Data Index: 522433 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0153. Min Act: -0.0004

Data Index: 467481 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0131. Min Act: -0.0004

Data Index: 474429 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0144. Min Act: -0.0004

Data Index: 287972 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0156. Min Act: -0.0004

Data Index: 333512 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0153. Min Act: -0.0004

Data Index: 775079 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0142. Min Act: -0.0004

Data Index: 889769 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0141. Min Act: -0.0004

Data Index: 175572 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0160. Min Act: -0.0004

Data Index: 401340 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0151. Min Act: -0.0004

Data Index: 1183436 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0150. Min Act: -0.0004

Data Index: 214594 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0163. Min Act: -0.0004

Data Index: 321013 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0130. Min Act: -0.0004

Data Index: 844746 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0122. Min Act: -0.0004

Data Index: 701603 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0156. Min Act: -0.0004

Data Index: 1156620 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0129. Min Act: -0.0004

Data Index: 1008568 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.0167. Min Range: -0.0167

Max Act: 0.0148. Min Act: -0.0004

Data Index: 446286 (C4 (Web Text))

Max Activating Token Index: 123