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

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

Neuron 4246 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9880. Min Range: -5.9880

Max Act: 5.9880. Min Act: -0.0000

Data Index: 864629 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 5.9880. Min Range: -5.9880

Max Act: 5.9879. Min Act: -0.0001

Data Index: 1308698 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 5.9880. Min Range: -5.9880

Max Act: 5.8199. Min Act: -0.0000

Data Index: 677932 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 5.9880. Min Range: -5.9880

Max Act: 5.6114. Min Act: -0.0001

Data Index: 724766 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 5.9880. Min Range: -5.9880

Max Act: 5.6450. Min Act: -0.0000

Data Index: 17409 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 5.9880. Min Range: -5.9880

Max Act: 5.6007. Min Act: -0.0000

Data Index: 218438 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 5.9880. Min Range: -5.9880

Max Act: 5.6156. Min Act: -0.0000

Data Index: 1270955 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 5.9880. Min Range: -5.9880

Max Act: 5.7982. Min Act: -0.0000

Data Index: 305656 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 5.9880. Min Range: -5.9880

Max Act: 5.3685. Min Act: -0.0001

Data Index: 1348459 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 5.9880. Min Range: -5.9880

Max Act: 5.4507. Min Act: -0.0000

Data Index: 304127 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 5.9880. Min Range: -5.9880

Max Act: 5.2507. Min Act: -0.0000

Data Index: 529013 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 5.9880. Min Range: -5.9880

Max Act: 5.2554. Min Act: -0.0001

Data Index: 256180 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 5.9880. Min Range: -5.9880

Max Act: 5.5902. Min Act: -0.0001

Data Index: 900597 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 5.9880. Min Range: -5.9880

Max Act: 4.8415. Min Act: -0.0001

Data Index: 763933 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 5.9880. Min Range: -5.9880

Max Act: 5.4942. Min Act: -0.0000

Data Index: 538570 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 5.9880. Min Range: -5.9880

Max Act: 5.0616. Min Act: -0.0000

Data Index: 970148 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 5.9880. Min Range: -5.9880

Max Act: 4.9330. Min Act: -0.0000

Data Index: 551387 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 5.9880. Min Range: -5.9880

Max Act: 4.6994. Min Act: -0.0000

Data Index: 1146761 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 5.9880. Min Range: -5.9880

Max Act: 4.8079. Min Act: -0.0001

Data Index: 851802 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 5.9880. Min Range: -5.9880

Max Act: 4.6392. Min Act: -0.0000

Data Index: 1319610 (C4 (Web Text))

Max Activating Token Index: 854