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

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

Neuron 3788 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0191. Min Act: -0.0001

Data Index: 1364485 (Python Code)

Max Activating Token Index: 127

Text #1

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0192. Min Act: -0.0001

Data Index: 280107 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0190. Min Act: -0.0001

Data Index: 1441427 (Python Code)

Max Activating Token Index: 1012

Text #3

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0174. Min Act: -0.0001

Data Index: 1399485 (Python Code)

Max Activating Token Index: 585

Text #4

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0174. Min Act: -0.0001

Data Index: 1364386 (Python Code)

Max Activating Token Index: 671

Text #5

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0165. Min Act: -0.0001

Data Index: 1626103 (Python Code)

Max Activating Token Index: 610

Text #6

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0174. Min Act: -0.0001

Data Index: 1439620 (Python Code)

Max Activating Token Index: 887

Text #7

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0174. Min Act: -0.0001

Data Index: 1185313 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0161. Min Act: -0.0001

Data Index: 1426569 (Python Code)

Max Activating Token Index: 278

Text #9

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0156. Min Act: -0.0001

Data Index: 849074 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0154. Min Act: -0.0001

Data Index: 1486747 (Python Code)

Max Activating Token Index: 242

Text #11

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0158. Min Act: -0.0001

Data Index: 1583307 (Python Code)

Max Activating Token Index: 257

Text #12

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0141. Min Act: -0.0001

Data Index: 577350 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0142. Min Act: -0.0001

Data Index: 35286 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0157. Min Act: -0.0001

Data Index: 1391913 (Python Code)

Max Activating Token Index: 546

Text #15

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0148. Min Act: -0.0001

Data Index: 1569327 (Python Code)

Max Activating Token Index: 878

Text #16

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0147. Min Act: -0.0001

Data Index: 1396425 (Python Code)

Max Activating Token Index: 107

Text #17

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0150. Min Act: -0.0001

Data Index: 1061399 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0140. Min Act: -0.0001

Data Index: 1351147 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0145. Min Act: -0.0001

Data Index: 890840 (C4 (Web Text))

Max Activating Token Index: 152