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

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

Neuron 3804 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0180. Min Act: -0.0001

Data Index: 1163442 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0176. Min Act: -0.0001

Data Index: 673476 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0172. Min Act: -0.0001

Data Index: 310738 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0175. Min Act: -0.0001

Data Index: 1214284 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0170. Min Act: -0.0001

Data Index: 748566 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0173. Min Act: -0.0001

Data Index: 1275401 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0170. Min Act: -0.0001

Data Index: 790309 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0172. Min Act: -0.0001

Data Index: 166702 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0166. Min Act: -0.0001

Data Index: 693200 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0169. Min Act: -0.0001

Data Index: 1165808 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0172. Min Act: -0.0001

Data Index: 1045129 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0170. Min Act: -0.0001

Data Index: 74401 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0167. Min Act: -0.0001

Data Index: 1115072 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0168. Min Act: -0.0001

Data Index: 26162 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0167. Min Act: -0.0001

Data Index: 68828 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0167. Min Act: -0.0001

Data Index: 497190 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0165. Min Act: -0.0001

Data Index: 903622 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0165. Min Act: -0.0001

Data Index: 132060 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0165. Min Act: -0.0001

Data Index: 1318394 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0164. Min Act: -0.0001

Data Index: 1605156 (Python Code)

Max Activating Token Index: 213