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

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

Neuron 1105 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: 0.0195. Min Range: -0.0195

Max Act: 0.0195. Min Act: -0.0006

Data Index: 823995 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0188. Min Act: -0.0006

Data Index: 1292132 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0181. Min Act: -0.0005

Data Index: 718102 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0185. Min Act: -0.0005

Data Index: 344524 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0179. Min Act: -0.0006

Data Index: 604620 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0175. Min Act: -0.0006

Data Index: 1512797 (Python Code)

Max Activating Token Index: 397

Text #6

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0178. Min Act: -0.0005

Data Index: 1242052 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0175. Min Act: -0.0006

Data Index: 2026 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0169. Min Act: -0.0006

Data Index: 227090 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0173. Min Act: -0.0006

Data Index: 991261 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0168. Min Act: -0.0005

Data Index: 1653038 (Python Code)

Max Activating Token Index: 678

Text #11

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0168. Min Act: -0.0005

Data Index: 1579042 (Python Code)

Max Activating Token Index: 276

Text #12

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0168. Min Act: -0.0006

Data Index: 1254041 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0159. Min Act: -0.0006

Data Index: 138081 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0166. Min Act: -0.0006

Data Index: 3729 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0163. Min Act: -0.0005

Data Index: 1439341 (Python Code)

Max Activating Token Index: 256

Text #16

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0160. Min Act: -0.0007

Data Index: 565553 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0164. Min Act: -0.0006

Data Index: 937180 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0162. Min Act: -0.0006

Data Index: 1500801 (Python Code)

Max Activating Token Index: 204

Text #19

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0162. Min Act: -0.0006

Data Index: 1337434 (C4 (Web Text))

Max Activating Token Index: 60