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

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

Neuron 1226 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3834. Min Range: -1.3834

Max Act: 1.3834. Min Act: -0.0001

Data Index: 815811 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 1.3834. Min Range: -1.3834

Max Act: 1.1413. Min Act: -0.0001

Data Index: 769459 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 1.3834. Min Range: -1.3834

Max Act: 1.1095. Min Act: -0.0001

Data Index: 1079899 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 1.3834. Min Range: -1.3834

Max Act: 1.0662. Min Act: -0.0001

Data Index: 48994 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 1.3834. Min Range: -1.3834

Max Act: 1.0035. Min Act: -0.0001

Data Index: 1482921 (Python Code)

Max Activating Token Index: 774

Text #5

Max Range: 1.3834. Min Range: -1.3834

Max Act: 1.0265. Min Act: -0.0001

Data Index: 1130610 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 1.3834. Min Range: -1.3834

Max Act: 1.0124. Min Act: -0.0001

Data Index: 209187 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 1.3834. Min Range: -1.3834

Max Act: 1.0469. Min Act: -0.0001

Data Index: 1377732 (Python Code)

Max Activating Token Index: 1008

Text #8

Max Range: 1.3834. Min Range: -1.3834

Max Act: 1.0147. Min Act: -0.0001

Data Index: 814047 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.9915. Min Act: -0.0001

Data Index: 198241 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.9672. Min Act: -0.0001

Data Index: 934354 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.9652. Min Act: -0.0001

Data Index: 160717 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.9439. Min Act: -0.0001

Data Index: 1132197 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.9223. Min Act: -0.0001

Data Index: 653619 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.9208. Min Act: -0.0001

Data Index: 777162 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.9181. Min Act: -0.0001

Data Index: 1230530 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.9033. Min Act: -0.0001

Data Index: 895119 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.8707. Min Act: -0.0001

Data Index: 217957 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.9568. Min Act: -0.0001

Data Index: 174027 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 1.3834. Min Range: -1.3834

Max Act: 0.9308. Min Act: -0.0001

Data Index: 950788 (C4 (Web Text))

Max Activating Token Index: 189