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

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

Neuron 4527 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1602. Min Act: -0.0002

Data Index: 143057 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1558. Min Act: -0.0002

Data Index: 181838 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1464. Min Act: -0.0002

Data Index: 874693 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1327. Min Act: -0.0002

Data Index: 40690 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1327. Min Act: -0.0002

Data Index: 274434 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1307. Min Act: -0.0002

Data Index: 668672 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1318. Min Act: -0.0002

Data Index: 262262 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1235. Min Act: -0.0002

Data Index: 963052 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1221. Min Act: -0.0002

Data Index: 243025 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1104. Min Act: -0.0002

Data Index: 248347 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1154. Min Act: -0.0002

Data Index: 525165 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1237. Min Act: -0.0002

Data Index: 1175952 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1191. Min Act: -0.0002

Data Index: 397902 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1235. Min Act: -0.0002

Data Index: 927076 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1141. Min Act: -0.0002

Data Index: 284263 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1173. Min Act: -0.0002

Data Index: 899976 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1090. Min Act: -0.0002

Data Index: 301748 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1123. Min Act: -0.0002

Data Index: 613949 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1157. Min Act: -0.0002

Data Index: 542722 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1152. Min Act: -0.0002

Data Index: 598559 (C4 (Web Text))

Max Activating Token Index: 234