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

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

Neuron 3775 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4925. Min Act: -0.0001

Data Index: 573292 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4406. Min Act: -0.0001

Data Index: 751117 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4331. Min Act: -0.0001

Data Index: 394527 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4394. Min Act: -0.0001

Data Index: 665689 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.3920. Min Act: -0.0001

Data Index: 598405 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4528. Min Act: -0.0001

Data Index: 1207455 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.3948. Min Act: -0.0001

Data Index: 7881 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4043. Min Act: -0.0001

Data Index: 1113386 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.3898. Min Act: -0.0001

Data Index: 909158 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4381. Min Act: -0.0001

Data Index: 388027 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4595. Min Act: -0.0001

Data Index: 123632 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4144. Min Act: -0.0001

Data Index: 235965 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4351. Min Act: -0.0001

Data Index: 123983 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4367. Min Act: -0.0001

Data Index: 1292077 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4243. Min Act: -0.0001

Data Index: 669543 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4127. Min Act: -0.0001

Data Index: 89230 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4315. Min Act: -0.0001

Data Index: 757096 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4110. Min Act: -0.0001

Data Index: 3054 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4135. Min Act: -0.0001

Data Index: 744553 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 0.4925. Min Range: -0.4925

Max Act: 0.4045. Min Act: -0.0001

Data Index: 764678 (C4 (Web Text))

Max Activating Token Index: 963