Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3026 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0188. Min Act: -0.0000

Data Index: 1160667 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0174. Min Act: -0.0000

Data Index: 1656861 (Python Code)

Max Activating Token Index: 783

Text #2

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0144. Min Act: -0.0000

Data Index: 1463792 (Python Code)

Max Activating Token Index: 813

Text #3

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0142. Min Act: -0.0000

Data Index: 1329706 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0155. Min Act: -0.0000

Data Index: 718947 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0136. Min Act: -0.0001

Data Index: 878898 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0149. Min Act: -0.0000

Data Index: 1492099 (Python Code)

Max Activating Token Index: 29

Text #7

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0149. Min Act: -0.0000

Data Index: 1268593 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0143. Min Act: -0.0000

Data Index: 762822 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0152. Min Act: -0.0000

Data Index: 680273 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0147. Min Act: -0.0000

Data Index: 588134 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0140. Min Act: -0.0000

Data Index: 512765 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0134. Min Act: -0.0000

Data Index: 503921 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0151. Min Act: -0.0000

Data Index: 971815 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0141. Min Act: -0.0000

Data Index: 716856 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0138. Min Act: -0.0000

Data Index: 749966 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0158. Min Act: -0.0000

Data Index: 1479564 (Python Code)

Max Activating Token Index: 290

Text #17

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0137. Min Act: -0.0000

Data Index: 1502512 (Python Code)

Max Activating Token Index: 46

Text #18

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0140. Min Act: -0.0000

Data Index: 853747 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 0.0188. Min Range: -0.0188

Max Act: 0.0147. Min Act: -0.0000

Data Index: 488672 (C4 (Web Text))

Max Activating Token Index: 410