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

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

Neuron 1065 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: 0.7690. Min Range: -0.7690

Max Act: 0.7690. Min Act: -0.0001

Data Index: 1197070 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.7249. Min Act: -0.0001

Data Index: 148406 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.7160. Min Act: -0.0002

Data Index: 934700 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.7140. Min Act: -0.0002

Data Index: 998532 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.7037. Min Act: -0.0002

Data Index: 255728 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.7451. Min Act: -0.0002

Data Index: 1087232 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.7229. Min Act: -0.0001

Data Index: 1312128 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.7221. Min Act: -0.0002

Data Index: 1043574 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.5665. Min Act: -0.0002

Data Index: 1118227 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.6821. Min Act: -0.0001

Data Index: 325016 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.5997. Min Act: -0.0002

Data Index: 927625 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.6962. Min Act: -0.0002

Data Index: 1248538 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.6726. Min Act: -0.0001

Data Index: 453237 (C4 (Web Text))

Max Activating Token Index: 390

Text #13

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.6459. Min Act: -0.0002

Data Index: 1059474 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.6837. Min Act: -0.0001

Data Index: 13003 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.6587. Min Act: -0.0001

Data Index: 355493 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.6797. Min Act: -0.0002

Data Index: 236399 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.6586. Min Act: -0.0002

Data Index: 1008095 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.6761. Min Act: -0.0002

Data Index: 1237402 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.6720. Min Act: -0.0001

Data Index: 356252 (C4 (Web Text))

Max Activating Token Index: 354