Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4171 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4751. Min Range: -1.4751

Max Act: 1.4751. Min Act: -0.0000

Data Index: 1129384 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 1.4751. Min Range: -1.4751

Max Act: 1.3561. Min Act: -0.0000

Data Index: 47620 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 1.4751. Min Range: -1.4751

Max Act: 1.1255. Min Act: -0.0000

Data Index: 519870 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 1.4751. Min Range: -1.4751

Max Act: 1.0244. Min Act: -0.0000

Data Index: 1065624 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 1.4751. Min Range: -1.4751

Max Act: 1.0923. Min Act: -0.0000

Data Index: 1160196 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 1.4751. Min Range: -1.4751

Max Act: 1.1242. Min Act: -0.0000

Data Index: 275839 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 1.4751. Min Range: -1.4751

Max Act: 1.0609. Min Act: -0.0000

Data Index: 608281 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.9871. Min Act: -0.0000

Data Index: 575751 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.9946. Min Act: -0.0000

Data Index: 434653 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 1.4751. Min Range: -1.4751

Max Act: 1.0196. Min Act: -0.0000

Data Index: 584157 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.9013. Min Act: -0.0000

Data Index: 455166 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.9575. Min Act: -0.0000

Data Index: 990727 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.8544. Min Act: -0.0000

Data Index: 427825 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.9493. Min Act: -0.0000

Data Index: 747926 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.9350. Min Act: -0.0000

Data Index: 871100 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.8689. Min Act: -0.0000

Data Index: 140907 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.9215. Min Act: -0.0000

Data Index: 1344163 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.8750. Min Act: -0.0000

Data Index: 1168465 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.8334. Min Act: 0.0000

Data Index: 872035 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 1.4751. Min Range: -1.4751

Max Act: 0.8932. Min Act: -0.0000

Data Index: 156664 (C4 (Web Text))

Max Activating Token Index: 203