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

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

Neuron 5064 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.4970. Min Act: -0.0000

Data Index: 816065 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.3305. Min Act: -0.0000

Data Index: 705414 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.1583. Min Act: -0.0000

Data Index: 848008 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.1201. Min Act: -0.0000

Data Index: 1296563 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.1279. Min Act: -0.0000

Data Index: 235034 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.1284. Min Act: -0.0000

Data Index: 186556 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.0986. Min Act: -0.0000

Data Index: 818200 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.1964. Min Act: -0.0000

Data Index: 122609 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.1380. Min Act: -0.0000

Data Index: 665845 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.0384. Min Act: -0.0000

Data Index: 196203 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.0990. Min Act: -0.0000

Data Index: 823373 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.0940. Min Act: -0.0000

Data Index: 892962 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.0527. Min Act: -0.0000

Data Index: 256536 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.0896. Min Act: -0.0000

Data Index: 695630 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.0685. Min Act: -0.0000

Data Index: 273109 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.0823. Min Act: -0.0000

Data Index: 672697 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.0807. Min Act: -0.0000

Data Index: 373421 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.1138. Min Act: -0.0000

Data Index: 900519 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.0687. Min Act: -0.0000

Data Index: 925400 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 1.4970. Min Range: -1.4970

Max Act: 1.0567. Min Act: -0.0000

Data Index: 411771 (C4 (Web Text))

Max Activating Token Index: 191