Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1824 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0200. Min Act: -0.0005

Data Index: 226865 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0182. Min Act: -0.0006

Data Index: 1564710 (Python Code)

Max Activating Token Index: 195

Text #2

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0186. Min Act: -0.0006

Data Index: 595667 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0177. Min Act: -0.0006

Data Index: 1001318 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0175. Min Act: -0.0006

Data Index: 1540591 (Python Code)

Max Activating Token Index: 904

Text #5

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0160. Min Act: -0.0006

Data Index: 1448786 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0166. Min Act: -0.0005

Data Index: 649218 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0158. Min Act: -0.0006

Data Index: 16351 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0153. Min Act: -0.0006

Data Index: 608085 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0168. Min Act: -0.0006

Data Index: 1612329 (Python Code)

Max Activating Token Index: 718

Text #10

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0153. Min Act: -0.0005

Data Index: 490998 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0168. Min Act: -0.0006

Data Index: 996869 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0160. Min Act: -0.0006

Data Index: 142149 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0160. Min Act: -0.0006

Data Index: 270325 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0155. Min Act: -0.0006

Data Index: 1414744 (Python Code)

Max Activating Token Index: 13

Text #15

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0166. Min Act: -0.0006

Data Index: 1477609 (Python Code)

Max Activating Token Index: 759

Text #16

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0157. Min Act: -0.0006

Data Index: 1494541 (Python Code)

Max Activating Token Index: 200

Text #17

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0160. Min Act: -0.0006

Data Index: 1566350 (Python Code)

Max Activating Token Index: 38

Text #18

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0160. Min Act: -0.0006

Data Index: 1639665 (Python Code)

Max Activating Token Index: 261

Text #19

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0163. Min Act: -0.0006

Data Index: 1627759 (Python Code)

Max Activating Token Index: 80