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

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

Neuron 2819 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: 0.0163. Min Range: -0.0163

Max Act: 0.0159. Min Act: -0.0001

Data Index: 1214814 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0152. Min Act: -0.0001

Data Index: 43403 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0147. Min Act: -0.0001

Data Index: 1174526 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0139. Min Act: -0.0001

Data Index: 304181 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0151. Min Act: -0.0001

Data Index: 1531861 (Python Code)

Max Activating Token Index: 608

Text #5

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0143. Min Act: -0.0001

Data Index: 796694 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0157. Min Act: -0.0001

Data Index: 1054837 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0149. Min Act: -0.0001

Data Index: 770562 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0145. Min Act: -0.0001

Data Index: 879042 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0136. Min Act: -0.0001

Data Index: 200125 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0136. Min Act: -0.0001

Data Index: 589950 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0163. Min Act: -0.0001

Data Index: 495625 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0138. Min Act: -0.0001

Data Index: 1385113 (Python Code)

Max Activating Token Index: 333

Text #13

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0136. Min Act: -0.0001

Data Index: 591556 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0137. Min Act: -0.0001

Data Index: 971237 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0130. Min Act: -0.0001

Data Index: 176732 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0131. Min Act: -0.0001

Data Index: 616999 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0130. Min Act: -0.0001

Data Index: 148864 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0130. Min Act: -0.0001

Data Index: 156653 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0136. Min Act: -0.0001

Data Index: 172714 (C4 (Web Text))

Max Activating Token Index: 82