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

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

Neuron 1120 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: 0.8788. Min Range: -0.8788

Max Act: 0.8661. Min Act: -0.0001

Data Index: 343500 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.8552. Min Act: -0.0001

Data Index: 567820 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.8601. Min Act: -0.0002

Data Index: 422491 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.8788. Min Act: -0.0002

Data Index: 627488 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.8655. Min Act: -0.0002

Data Index: 560497 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.7893. Min Act: -0.0002

Data Index: 510152 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.7421. Min Act: -0.0002

Data Index: 899665 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.8337. Min Act: -0.0002

Data Index: 541360 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.8197. Min Act: -0.0001

Data Index: 177627 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.7692. Min Act: -0.0002

Data Index: 1076096 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.6938. Min Act: -0.0002

Data Index: 1052242 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.7354. Min Act: -0.0002

Data Index: 811199 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.7315. Min Act: -0.0001

Data Index: 1039556 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.6544. Min Act: -0.0002

Data Index: 83315 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.7740. Min Act: -0.0002

Data Index: 1111127 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.7307. Min Act: -0.0001

Data Index: 240503 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.6618. Min Act: -0.0001

Data Index: 668605 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.6792. Min Act: -0.0002

Data Index: 1041625 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.7471. Min Act: -0.0002

Data Index: 673721 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.7446. Min Act: -0.0002

Data Index: 236135 (C4 (Web Text))

Max Activating Token Index: 887