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

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

Neuron 3232 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.6495. Min Act: -0.0001

Data Index: 731807 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.6636. Min Act: -0.0001

Data Index: 957153 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.6188. Min Act: -0.0001

Data Index: 38584 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.6064. Min Act: -0.0001

Data Index: 1334498 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5868. Min Act: -0.0001

Data Index: 1165000 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.6205. Min Act: -0.0001

Data Index: 439566 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5666. Min Act: -0.0001

Data Index: 373496 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.6052. Min Act: -0.0001

Data Index: 1358322 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5738. Min Act: -0.0001

Data Index: 868794 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5502. Min Act: -0.0001

Data Index: 324203 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5658. Min Act: -0.0001

Data Index: 235497 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5602. Min Act: -0.0001

Data Index: 229025 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5522. Min Act: -0.0001

Data Index: 383589 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5675. Min Act: -0.0001

Data Index: 985417 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5818. Min Act: -0.0001

Data Index: 328011 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5246. Min Act: -0.0001

Data Index: 1179375 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5165. Min Act: -0.0001

Data Index: 307960 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5199. Min Act: -0.0001

Data Index: 929252 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5833. Min Act: -0.0001

Data Index: 279241 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5281. Min Act: -0.0001

Data Index: 305461 (C4 (Web Text))

Max Activating Token Index: 242