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

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

Neuron 1303 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: 0.3654. Min Range: -0.3654

Max Act: 0.3567. Min Act: -0.0000

Data Index: 1629140 (Python Code)

Max Activating Token Index: 140

Text #1

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3654. Min Act: -0.0000

Data Index: 177908 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3491. Min Act: -0.0000

Data Index: 582309 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3531. Min Act: -0.0000

Data Index: 1550975 (Python Code)

Max Activating Token Index: 412

Text #4

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3613. Min Act: -0.0000

Data Index: 688158 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3480. Min Act: -0.0000

Data Index: 1319312 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3323. Min Act: -0.0000

Data Index: 47110 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3482. Min Act: -0.0000

Data Index: 1182397 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3624. Min Act: -0.0000

Data Index: 384453 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3380. Min Act: -0.0000

Data Index: 820894 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3407. Min Act: -0.0000

Data Index: 47489 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3158. Min Act: -0.0000

Data Index: 1151720 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3134. Min Act: -0.0000

Data Index: 1568975 (Python Code)

Max Activating Token Index: 259

Text #13

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3088. Min Act: -0.0000

Data Index: 900652 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3091. Min Act: -0.0000

Data Index: 206826 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3400. Min Act: -0.0000

Data Index: 272793 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.2958. Min Act: -0.0000

Data Index: 1568719 (Python Code)

Max Activating Token Index: 808

Text #17

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.2851. Min Act: -0.0000

Data Index: 814966 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.2938. Min Act: -0.0000

Data Index: 1466868 (Python Code)

Max Activating Token Index: 108

Text #19

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.2942. Min Act: -0.0000

Data Index: 1499851 (Python Code)

Max Activating Token Index: 120