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

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

Neuron 3863 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.5870. Min Act: -0.0001

Data Index: 508050 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.5347. Min Act: -0.0001

Data Index: 267216 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.5439. Min Act: -0.0001

Data Index: 337536 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.5359. Min Act: -0.0001

Data Index: 1229937 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.4916. Min Act: -0.0001

Data Index: 313399 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.4517. Min Act: -0.0001

Data Index: 1271514 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.4639. Min Act: -0.0001

Data Index: 1324022 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.5081. Min Act: -0.0001

Data Index: 660191 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.4641. Min Act: -0.0001

Data Index: 137709 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.4782. Min Act: -0.0001

Data Index: 1015574 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.4756. Min Act: -0.0001

Data Index: 90226 (C4 (Web Text))

Max Activating Token Index: 954

Text #11

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.4763. Min Act: -0.0001

Data Index: 822749 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.4150. Min Act: -0.0001

Data Index: 520122 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.4750. Min Act: -0.0001

Data Index: 35879 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.4398. Min Act: -0.0001

Data Index: 234991 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.4483. Min Act: -0.0001

Data Index: 718541 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.4453. Min Act: -0.0001

Data Index: 897130 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.4709. Min Act: -0.0001

Data Index: 1140685 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.4499. Min Act: -0.0001

Data Index: 1308514 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 0.5870. Min Range: -0.5870

Max Act: 0.4105. Min Act: -0.0001

Data Index: 301142 (C4 (Web Text))

Max Activating Token Index: 341