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

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

Neuron 4013 in Layer 1

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: 0.0240. Min Range: -0.0240

Max Act: 0.0240. Min Act: -0.0002

Data Index: 904356 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0216. Min Act: -0.0002

Data Index: 1120888 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0194. Min Act: -0.0002

Data Index: 1626084 (Python Code)

Max Activating Token Index: 883

Text #3

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0195. Min Act: -0.0002

Data Index: 1375523 (Python Code)

Max Activating Token Index: 536

Text #4

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0186. Min Act: -0.0002

Data Index: 966473 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0186. Min Act: -0.0002

Data Index: 1289857 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0182. Min Act: -0.0002

Data Index: 1472566 (Python Code)

Max Activating Token Index: 358

Text #7

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1430806 (Python Code)

Max Activating Token Index: 681

Text #8

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1533042 (Python Code)

Max Activating Token Index: 798

Text #9

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0163. Min Act: -0.0002

Data Index: 1528792 (Python Code)

Max Activating Token Index: 709

Text #10

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0159. Min Act: -0.0002

Data Index: 1621002 (Python Code)

Max Activating Token Index: 823

Text #11

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0160. Min Act: -0.0002

Data Index: 155036 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0165. Min Act: -0.0002

Data Index: 50475 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0163. Min Act: -0.0002

Data Index: 850260 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0163. Min Act: -0.0002

Data Index: 1638150 (Python Code)

Max Activating Token Index: 671

Text #15

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0161. Min Act: -0.0002

Data Index: 1441725 (Python Code)

Max Activating Token Index: 359

Text #16

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0156. Min Act: -0.0002

Data Index: 734801 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0158. Min Act: -0.0002

Data Index: 1561968 (Python Code)

Max Activating Token Index: 348

Text #18

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0158. Min Act: -0.0002

Data Index: 8105 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 0.0240. Min Range: -0.0240

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1588240 (Python Code)

Max Activating Token Index: 495