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

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

Neuron 3966 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.9509. Min Act: -0.0002

Data Index: 42261 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8939. Min Act: -0.0002

Data Index: 518829 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8864. Min Act: -0.0002

Data Index: 540919 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8840. Min Act: -0.0002

Data Index: 195053 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8715. Min Act: -0.0002

Data Index: 510290 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8536. Min Act: -0.0002

Data Index: 1112726 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8516. Min Act: -0.0002

Data Index: 117824 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8373. Min Act: -0.0002

Data Index: 948880 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8563. Min Act: -0.0002

Data Index: 917671 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8458. Min Act: -0.0002

Data Index: 1158706 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8448. Min Act: -0.0002

Data Index: 964129 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8415. Min Act: -0.0002

Data Index: 827511 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8227. Min Act: -0.0002

Data Index: 1191601 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8061. Min Act: -0.0002

Data Index: 1290204 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8228. Min Act: -0.0002

Data Index: 84761 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8136. Min Act: -0.0002

Data Index: 1237219 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8146. Min Act: -0.0002

Data Index: 456424 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7966. Min Act: -0.0002

Data Index: 147383 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.8035. Min Act: -0.0002

Data Index: 1321472 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.9509. Min Range: -0.9509

Max Act: 0.7917. Min Act: -0.0002

Data Index: 1113850 (C4 (Web Text))

Max Activating Token Index: 685