Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1593 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5968. Min Act: -0.0001

Data Index: 292691 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5714. Min Act: -0.0001

Data Index: 468498 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5603. Min Act: -0.0001

Data Index: 436896 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.5595. Min Act: -0.0001

Data Index: 538948 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4697. Min Act: -0.0001

Data Index: 336872 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4874. Min Act: -0.0001

Data Index: 1325409 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4883. Min Act: -0.0001

Data Index: 790805 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4652. Min Act: -0.0001

Data Index: 1140438 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4477. Min Act: -0.0001

Data Index: 908023 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4209. Min Act: -0.0001

Data Index: 1211851 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4445. Min Act: -0.0001

Data Index: 966172 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4415. Min Act: -0.0001

Data Index: 571961 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4465. Min Act: -0.0001

Data Index: 518306 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4226. Min Act: -0.0001

Data Index: 1011186 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4289. Min Act: -0.0001

Data Index: 691479 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4324. Min Act: -0.0001

Data Index: 1278898 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4479. Min Act: -0.0001

Data Index: 212052 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4139. Min Act: -0.0001

Data Index: 73909 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4128. Min Act: -0.0001

Data Index: 146522 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 0.5968. Min Range: -0.5968

Max Act: 0.4062. Min Act: -0.0001

Data Index: 337160 (C4 (Web Text))

Max Activating Token Index: 603