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

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

Neuron 1383 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.9009. Min Act: -0.0000

Data Index: 308435 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.8849. Min Act: -0.0000

Data Index: 1246757 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.9028. Min Act: -0.0001

Data Index: 729201 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.7489. Min Act: -0.0001

Data Index: 18509 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.7421. Min Act: -0.0001

Data Index: 543673 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.7074. Min Act: -0.0000

Data Index: 171282 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.6624. Min Act: -0.0001

Data Index: 138526 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.6328. Min Act: -0.0000

Data Index: 364720 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.5108. Min Act: -0.0000

Data Index: 1180513 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.5811. Min Act: -0.0000

Data Index: 93412 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.5662. Min Act: -0.0000

Data Index: 116483 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.5382. Min Act: -0.0000

Data Index: 825528 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.5598. Min Act: -0.0000

Data Index: 667199 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.5176. Min Act: -0.0000

Data Index: 282494 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.5599. Min Act: -0.0000

Data Index: 1241691 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.4724. Min Act: -0.0000

Data Index: 533984 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.4934. Min Act: -0.0000

Data Index: 849080 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.4748. Min Act: -0.0000

Data Index: 728511 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.4657. Min Act: -0.0000

Data Index: 209546 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.5138. Min Act: -0.0001

Data Index: 896032 (C4 (Web Text))

Max Activating Token Index: 504