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

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

Neuron 1507 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0181. Min Act: -0.0006

Data Index: 727313 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0177. Min Act: -0.0006

Data Index: 158405 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0180. Min Act: -0.0006

Data Index: 26296 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0175. Min Act: -0.0005

Data Index: 1451644 (Python Code)

Max Activating Token Index: 765

Text #4

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0174. Min Act: -0.0006

Data Index: 962947 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0172. Min Act: -0.0006

Data Index: 931659 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0177. Min Act: -0.0006

Data Index: 840764 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0171. Min Act: -0.0006

Data Index: 273172 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0170. Min Act: -0.0006

Data Index: 393758 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0169. Min Act: -0.0006

Data Index: 512176 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0173. Min Act: -0.0006

Data Index: 219506 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0169. Min Act: -0.0005

Data Index: 1560094 (Python Code)

Max Activating Token Index: 123

Text #12

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0169. Min Act: -0.0005

Data Index: 265549 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0168. Min Act: -0.0006

Data Index: 280224 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0168. Min Act: -0.0006

Data Index: 876073 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0167. Min Act: -0.0006

Data Index: 1453363 (Python Code)

Max Activating Token Index: 649

Text #16

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0170. Min Act: -0.0006

Data Index: 836388 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0161. Min Act: -0.0005

Data Index: 716288 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0165. Min Act: -0.0006

Data Index: 897403 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 0.0181. Min Range: -0.0181

Max Act: 0.0165. Min Act: -0.0005

Data Index: 1360705 (Python Code)

Max Activating Token Index: 184