Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 954 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0225. Min Act: -0.0006

Data Index: 1484172 (Python Code)

Max Activating Token Index: 665

Text #1

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0198. Min Act: -0.0006

Data Index: 1453013 (Python Code)

Max Activating Token Index: 626

Text #2

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0197. Min Act: -0.0006

Data Index: 769124 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0200. Min Act: -0.0006

Data Index: 144687 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0179. Min Act: -0.0006

Data Index: 1455248 (Python Code)

Max Activating Token Index: 633

Text #5

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0182. Min Act: -0.0006

Data Index: 1565827 (Python Code)

Max Activating Token Index: 429

Text #6

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0180. Min Act: -0.0006

Data Index: 1306110 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0175. Min Act: -0.0006

Data Index: 1082872 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0181. Min Act: -0.0006

Data Index: 831660 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0163. Min Act: -0.0006

Data Index: 1475654 (Python Code)

Max Activating Token Index: 872

Text #10

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0170. Min Act: -0.0006

Data Index: 830352 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0177. Min Act: -0.0006

Data Index: 1416352 (Python Code)

Max Activating Token Index: 538

Text #12

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0173. Min Act: -0.0006

Data Index: 574174 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0167. Min Act: -0.0006

Data Index: 1594184 (Python Code)

Max Activating Token Index: 124

Text #14

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1545097 (Python Code)

Max Activating Token Index: 979

Text #15

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0166. Min Act: -0.0006

Data Index: 1425927 (Python Code)

Max Activating Token Index: 224

Text #16

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0154. Min Act: -0.0006

Data Index: 722343 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0165. Min Act: -0.0006

Data Index: 905384 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0171. Min Act: -0.0006

Data Index: 236495 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 0.0225. Min Range: -0.0225

Max Act: 0.0160. Min Act: -0.0006

Data Index: 360971 (C4 (Web Text))

Max Activating Token Index: 278