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

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

Neuron 969 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7228. Min Range: -2.7228

Max Act: 2.7228. Min Act: -0.0000

Data Index: 1326132 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 2.7228. Min Range: -2.7228

Max Act: 2.2852. Min Act: -0.0000

Data Index: 672867 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 2.7228. Min Range: -2.7228

Max Act: 1.9568. Min Act: -0.0001

Data Index: 1164603 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 2.7228. Min Range: -2.7228

Max Act: 1.8554. Min Act: -0.0000

Data Index: 173432 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 2.7228. Min Range: -2.7228

Max Act: 1.7394. Min Act: -0.0000

Data Index: 27005 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 2.7228. Min Range: -2.7228

Max Act: 1.5770. Min Act: -0.0000

Data Index: 241876 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 2.7228. Min Range: -2.7228

Max Act: 1.4133. Min Act: -0.0000

Data Index: 1331923 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 2.7228. Min Range: -2.7228

Max Act: 1.4930. Min Act: -0.0000

Data Index: 739205 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 2.7228. Min Range: -2.7228

Max Act: 1.4826. Min Act: -0.0000

Data Index: 977012 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 2.7228. Min Range: -2.7228

Max Act: 1.3340. Min Act: -0.0000

Data Index: 1126020 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 2.7228. Min Range: -2.7228

Max Act: 1.4163. Min Act: -0.0000

Data Index: 96761 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 2.7228. Min Range: -2.7228

Max Act: 1.3118. Min Act: -0.0000

Data Index: 1331359 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 2.7228. Min Range: -2.7228

Max Act: 1.2726. Min Act: -0.0000

Data Index: 633351 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 2.7228. Min Range: -2.7228

Max Act: 1.3140. Min Act: -0.0000

Data Index: 1137633 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 2.7228. Min Range: -2.7228

Max Act: 1.4039. Min Act: -0.0000

Data Index: 597494 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 2.7228. Min Range: -2.7228

Max Act: 1.2789. Min Act: -0.0000

Data Index: 668323 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 2.7228. Min Range: -2.7228

Max Act: 1.2636. Min Act: -0.0001

Data Index: 391747 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 2.7228. Min Range: -2.7228

Max Act: 1.2500. Min Act: -0.0000

Data Index: 876165 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 2.7228. Min Range: -2.7228

Max Act: 1.2432. Min Act: -0.0000

Data Index: 1180846 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 2.7228. Min Range: -2.7228

Max Act: 1.1079. Min Act: -0.0000

Data Index: 534053 (C4 (Web Text))

Max Activating Token Index: 173