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

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

Neuron 2587 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.4635. Min Act: -0.0001

Data Index: 50184 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.3935. Min Act: -0.0001

Data Index: 1267252 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.2983. Min Act: -0.0001

Data Index: 725579 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.2901. Min Act: -0.0001

Data Index: 407935 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.3386. Min Act: -0.0001

Data Index: 923578 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.2867. Min Act: -0.0001

Data Index: 996076 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.2647. Min Act: -0.0001

Data Index: 67582 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.3150. Min Act: -0.0002

Data Index: 1214254 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.2954. Min Act: -0.0001

Data Index: 725009 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.2186. Min Act: -0.0001

Data Index: 380702 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.2365. Min Act: -0.0001

Data Index: 894238 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.2879. Min Act: -0.0001

Data Index: 714719 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.1601. Min Act: -0.0001

Data Index: 223494 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.1956. Min Act: -0.0002

Data Index: 730694 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.1469. Min Act: -0.0001

Data Index: 985960 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.1455. Min Act: -0.0001

Data Index: 414747 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.1754. Min Act: -0.0001

Data Index: 1059362 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.2381. Min Act: -0.0001

Data Index: 928617 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.1792. Min Act: -0.0001

Data Index: 944809 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 1.4635. Min Range: -1.4635

Max Act: 1.2177. Min Act: -0.0001

Data Index: 279154 (C4 (Web Text))

Max Activating Token Index: 470