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

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

Neuron 741 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8310. Min Range: -2.8310

Max Act: 2.8310. Min Act: -0.0000

Data Index: 199385 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 2.8310. Min Range: -2.8310

Max Act: 2.7786. Min Act: -0.0000

Data Index: 471500 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 2.8310. Min Range: -2.8310

Max Act: 2.5364. Min Act: -0.0000

Data Index: 76065 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 2.8310. Min Range: -2.8310

Max Act: 2.1946. Min Act: -0.0000

Data Index: 1114204 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 2.8310. Min Range: -2.8310

Max Act: 2.2958. Min Act: -0.0000

Data Index: 823647 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 2.8310. Min Range: -2.8310

Max Act: 2.2273. Min Act: -0.0000

Data Index: 1279143 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 2.8310. Min Range: -2.8310

Max Act: 2.2164. Min Act: -0.0000

Data Index: 1154485 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 2.8310. Min Range: -2.8310

Max Act: 2.1646. Min Act: -0.0000

Data Index: 644445 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 2.8310. Min Range: -2.8310

Max Act: 2.0530. Min Act: -0.0000

Data Index: 41672 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 2.8310. Min Range: -2.8310

Max Act: 2.0247. Min Act: -0.0000

Data Index: 511599 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 2.8310. Min Range: -2.8310

Max Act: 2.1046. Min Act: -0.0000

Data Index: 111128 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 2.8310. Min Range: -2.8310

Max Act: 2.0872. Min Act: -0.0000

Data Index: 867678 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 2.8310. Min Range: -2.8310

Max Act: 1.9479. Min Act: -0.0000

Data Index: 870121 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 2.8310. Min Range: -2.8310

Max Act: 1.9250. Min Act: -0.0000

Data Index: 3876 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 2.8310. Min Range: -2.8310

Max Act: 2.0529. Min Act: -0.0000

Data Index: 548551 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 2.8310. Min Range: -2.8310

Max Act: 1.9014. Min Act: -0.0000

Data Index: 1216726 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 2.8310. Min Range: -2.8310

Max Act: 1.9892. Min Act: -0.0000

Data Index: 761907 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 2.8310. Min Range: -2.8310

Max Act: 1.9804. Min Act: -0.0000

Data Index: 469437 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 2.8310. Min Range: -2.8310

Max Act: 1.9629. Min Act: -0.0000

Data Index: 771624 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 2.8310. Min Range: -2.8310

Max Act: 1.9440. Min Act: -0.0000

Data Index: 635945 (C4 (Web Text))

Max Activating Token Index: 47