Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3095 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0218. Min Act: -0.0003

Data Index: 858305 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0173. Min Act: -0.0004

Data Index: 814669 (C4 (Web Text))

Max Activating Token Index: 499

Text #2

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0172. Min Act: -0.0003

Data Index: 32843 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0165. Min Act: -0.0003

Data Index: 258684 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0159. Min Act: -0.0003

Data Index: 861396 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0157. Min Act: -0.0003

Data Index: 783575 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0157. Min Act: -0.0003

Data Index: 1004405 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0163. Min Act: -0.0003

Data Index: 1039720 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0156. Min Act: -0.0003

Data Index: 890084 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0163. Min Act: -0.0003

Data Index: 98915 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0161. Min Act: -0.0004

Data Index: 619153 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0151. Min Act: -0.0003

Data Index: 960838 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0158. Min Act: -0.0003

Data Index: 1114514 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0150. Min Act: -0.0003

Data Index: 34016 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0142. Min Act: -0.0003

Data Index: 1271148 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0142. Min Act: -0.0003

Data Index: 1283096 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0160. Min Act: -0.0003

Data Index: 1290236 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0143. Min Act: -0.0003

Data Index: 1049624 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0145. Min Act: -0.0003

Data Index: 1027157 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0145. Min Act: -0.0003

Data Index: 1333184 (C4 (Web Text))

Max Activating Token Index: 648