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

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

Neuron 5635 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0231. Min Act: -0.0001

Data Index: 1411635 (Python Code)

Max Activating Token Index: 538

Text #1

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0211. Min Act: -0.0001

Data Index: 122578 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0189. Min Act: -0.0001

Data Index: 1237677 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0189. Min Act: -0.0001

Data Index: 609557 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0190. Min Act: -0.0001

Data Index: 1083408 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0177. Min Act: -0.0001

Data Index: 1400881 (Python Code)

Max Activating Token Index: 975

Text #6

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0186. Min Act: -0.0001

Data Index: 6958 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0201. Min Act: -0.0001

Data Index: 1643141 (Python Code)

Max Activating Token Index: 139

Text #8

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0183. Min Act: -0.0001

Data Index: 311464 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0181. Min Act: -0.0001

Data Index: 1147343 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0190. Min Act: -0.0001

Data Index: 441806 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0162. Min Act: -0.0001

Data Index: 1046758 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0182. Min Act: -0.0002

Data Index: 1649080 (Python Code)

Max Activating Token Index: 752

Text #13

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0178. Min Act: -0.0001

Data Index: 1607680 (Python Code)

Max Activating Token Index: 718

Text #14

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0169. Min Act: -0.0001

Data Index: 1070139 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0159. Min Act: -0.0001

Data Index: 1476415 (Python Code)

Max Activating Token Index: 914

Text #16

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0166. Min Act: -0.0001

Data Index: 1521977 (Python Code)

Max Activating Token Index: 27

Text #17

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0163. Min Act: -0.0001

Data Index: 1503673 (Python Code)

Max Activating Token Index: 338

Text #18

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0169. Min Act: -0.0001

Data Index: 1023989 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0165. Min Act: -0.0001

Data Index: 1458031 (Python Code)

Max Activating Token Index: 558