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

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

Neuron 4415 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: 0.9599. Min Range: -0.9599

Max Act: 0.9599. Min Act: -0.0001

Data Index: 948019 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.7626. Min Act: -0.0001

Data Index: 919602 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8450. Min Act: -0.0001

Data Index: 607327 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8308. Min Act: -0.0001

Data Index: 107691 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8325. Min Act: -0.0001

Data Index: 914862 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.7944. Min Act: -0.0001

Data Index: 1094637 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8529. Min Act: -0.0001

Data Index: 552056 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8660. Min Act: -0.0001

Data Index: 619394 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8109. Min Act: -0.0001

Data Index: 762247 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.7844. Min Act: -0.0001

Data Index: 396746 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.9042. Min Act: -0.0001

Data Index: 998465 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.9192. Min Act: -0.0001

Data Index: 1330251 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.7857. Min Act: -0.0001

Data Index: 492616 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8190. Min Act: -0.0001

Data Index: 204648 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8942. Min Act: -0.0001

Data Index: 496745 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.7970. Min Act: -0.0001

Data Index: 590132 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.7441. Min Act: -0.0001

Data Index: 1225316 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.7505. Min Act: -0.0001

Data Index: 378724 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8611. Min Act: -0.0001

Data Index: 56153 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.9599. Min Range: -0.9599

Max Act: 0.8574. Min Act: -0.0001

Data Index: 1170951 (C4 (Web Text))

Max Activating Token Index: 871