Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1635 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1046. Min Range: -1.1046

Max Act: 1.1046. Min Act: -0.0001

Data Index: 216553 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 1.1046. Min Range: -1.1046

Max Act: 1.0719. Min Act: -0.0001

Data Index: 530677 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 1.1046. Min Range: -1.1046

Max Act: 1.0604. Min Act: -0.0001

Data Index: 142258 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8834. Min Act: -0.0001

Data Index: 94756 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.9109. Min Act: -0.0001

Data Index: 198465 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.9105. Min Act: -0.0001

Data Index: 956934 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8893. Min Act: -0.0001

Data Index: 389767 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8892. Min Act: -0.0001

Data Index: 403017 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8216. Min Act: -0.0001

Data Index: 252264 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8303. Min Act: -0.0001

Data Index: 835342 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.8003. Min Act: -0.0001

Data Index: 453329 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7672. Min Act: -0.0001

Data Index: 1045078 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7672. Min Act: -0.0001

Data Index: 184752 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7513. Min Act: -0.0001

Data Index: 525851 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7986. Min Act: -0.0001

Data Index: 793050 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7974. Min Act: -0.0001

Data Index: 646529 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7387. Min Act: -0.0001

Data Index: 816230 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7391. Min Act: -0.0001

Data Index: 1292606 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.6307. Min Act: -0.0001

Data Index: 460311 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 1.1046. Min Range: -1.1046

Max Act: 0.7271. Min Act: -0.0001

Data Index: 1041310 (C4 (Web Text))

Max Activating Token Index: 197