Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2027 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1031. Min Act: -0.0005

Data Index: 392930 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1044. Min Act: -0.0005

Data Index: 436 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.1088. Min Act: -0.0005

Data Index: 900377 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0925. Min Act: -0.0005

Data Index: 541085 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0958. Min Act: -0.0005

Data Index: 363486 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0969. Min Act: -0.0005

Data Index: 1230146 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0964. Min Act: -0.0005

Data Index: 770829 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0933. Min Act: -0.0005

Data Index: 371252 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0971. Min Act: -0.0005

Data Index: 1219835 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0924. Min Act: -0.0005

Data Index: 1077711 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0954. Min Act: -0.0005

Data Index: 505147 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0943. Min Act: -0.0005

Data Index: 671574 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0882. Min Act: -0.0005

Data Index: 233145 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0911. Min Act: -0.0005

Data Index: 1284084 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0930. Min Act: -0.0005

Data Index: 115992 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0910. Min Act: -0.0005

Data Index: 1341821 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0890. Min Act: -0.0005

Data Index: 1234330 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0931. Min Act: -0.0005

Data Index: 272956 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0884. Min Act: -0.0005

Data Index: 688526 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 0.1088. Min Range: -0.1088

Max Act: 0.0913. Min Act: -0.0005

Data Index: 844750 (C4 (Web Text))

Max Activating Token Index: 441