Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 794 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.4893. Min Act: -0.0001

Data Index: 1299903 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.4546. Min Act: -0.0001

Data Index: 852056 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.0993. Min Act: -0.0001

Data Index: 423908 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.4967. Min Act: -0.0001

Data Index: 1162891 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.2487. Min Act: -0.0001

Data Index: 1335789 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.4840. Min Act: -0.0001

Data Index: 1134069 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.4465. Min Act: -0.0001

Data Index: 737753 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.2556. Min Act: -0.0001

Data Index: 957293 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.2877. Min Act: -0.0001

Data Index: 1355518 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.3096. Min Act: -0.0001

Data Index: 32724 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.3556. Min Act: -0.0001

Data Index: 470890 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.3203. Min Act: -0.0001

Data Index: 1349532 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.2358. Min Act: -0.0001

Data Index: 1119220 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.3722. Min Act: -0.0001

Data Index: 221180 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.2166. Min Act: -0.0001

Data Index: 886924 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.1244. Min Act: -0.0001

Data Index: 1207727 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.1539. Min Act: -0.0001

Data Index: 1031687 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.1030. Min Act: -0.0001

Data Index: 883648 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.1883. Min Act: -0.0001

Data Index: 1327288 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 1.4967. Min Range: -1.4967

Max Act: 1.1080. Min Act: -0.0001

Data Index: 314114 (C4 (Web Text))

Max Activating Token Index: 389