Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3283 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0179. Min Act: -0.0002

Data Index: 268344 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0145. Min Act: -0.0002

Data Index: 473307 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0139. Min Act: -0.0002

Data Index: 144723 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1043583 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1059189 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1141971 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0134. Min Act: -0.0002

Data Index: 712562 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0133. Min Act: -0.0002

Data Index: 658150 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0132. Min Act: -0.0002

Data Index: 1131756 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0132. Min Act: -0.0002

Data Index: 401642 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0131. Min Act: -0.0002

Data Index: 550327 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0130. Min Act: -0.0002

Data Index: 1254597 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0130. Min Act: -0.0002

Data Index: 1332447 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0128. Min Act: -0.0002

Data Index: 887425 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0128. Min Act: -0.0002

Data Index: 549062 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0128. Min Act: -0.0002

Data Index: 684639 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0127. Min Act: -0.0002

Data Index: 1274880 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0126. Min Act: -0.0002

Data Index: 975247 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0126. Min Act: -0.0002

Data Index: 1312108 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0125. Min Act: -0.0002

Data Index: 1122737 (C4 (Web Text))

Max Activating Token Index: 871