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

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

Neuron 861 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0864. Min Range: -1.0864

Max Act: 1.0620. Min Act: -0.0001

Data Index: 221898 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 1.0864. Min Range: -1.0864

Max Act: 1.0529. Min Act: -0.0001

Data Index: 145041 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 1.0864. Min Range: -1.0864

Max Act: 0.9574. Min Act: -0.0001

Data Index: 295203 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 1.0864. Min Range: -1.0864

Max Act: 1.0756. Min Act: -0.0001

Data Index: 1108572 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 1.0864. Min Range: -1.0864

Max Act: 1.0864. Min Act: -0.0001

Data Index: 188006 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 1.0864. Min Range: -1.0864

Max Act: 1.0129. Min Act: -0.0001

Data Index: 406483 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 1.0864. Min Range: -1.0864

Max Act: 0.9332. Min Act: -0.0001

Data Index: 707011 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 1.0864. Min Range: -1.0864

Max Act: 0.8728. Min Act: -0.0001

Data Index: 1083501 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 1.0864. Min Range: -1.0864

Max Act: 0.9126. Min Act: -0.0001

Data Index: 552249 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 1.0864. Min Range: -1.0864

Max Act: 0.8400. Min Act: -0.0001

Data Index: 74591 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 1.0864. Min Range: -1.0864

Max Act: 0.8976. Min Act: -0.0001

Data Index: 1319236 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 1.0864. Min Range: -1.0864

Max Act: 0.9400. Min Act: -0.0001

Data Index: 1261194 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 1.0864. Min Range: -1.0864

Max Act: 0.8176. Min Act: -0.0001

Data Index: 1204260 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 1.0864. Min Range: -1.0864

Max Act: 0.9083. Min Act: -0.0001

Data Index: 741622 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 1.0864. Min Range: -1.0864

Max Act: 0.7859. Min Act: -0.0001

Data Index: 269745 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 1.0864. Min Range: -1.0864

Max Act: 0.8509. Min Act: -0.0001

Data Index: 50499 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 1.0864. Min Range: -1.0864

Max Act: 0.7771. Min Act: -0.0001

Data Index: 64538 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 1.0864. Min Range: -1.0864

Max Act: 0.7803. Min Act: -0.0001

Data Index: 706710 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 1.0864. Min Range: -1.0864

Max Act: 0.8017. Min Act: -0.0001

Data Index: 1219410 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 1.0864. Min Range: -1.0864

Max Act: 0.8069. Min Act: -0.0001

Data Index: 113113 (C4 (Web Text))

Max Activating Token Index: 71