Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2271 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.5919. Min Act: -0.0001

Data Index: 704430 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.4887. Min Act: -0.0001

Data Index: 1601145 (Python Code)

Max Activating Token Index: 649

Text #2

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.4416. Min Act: -0.0001

Data Index: 1450050 (Python Code)

Max Activating Token Index: 360

Text #3

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.4184. Min Act: -0.0001

Data Index: 650634 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.3414. Min Act: -0.0000

Data Index: 953077 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.3315. Min Act: -0.0001

Data Index: 719692 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.3169. Min Act: -0.0001

Data Index: 1607317 (Python Code)

Max Activating Token Index: 104

Text #7

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.2355. Min Act: -0.0000

Data Index: 890122 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.2738. Min Act: -0.0000

Data Index: 935235 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.2391. Min Act: -0.0000

Data Index: 1324993 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.2944. Min Act: -0.0001

Data Index: 202919 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.2442. Min Act: -0.0001

Data Index: 766492 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.2333. Min Act: -0.0001

Data Index: 1517215 (Python Code)

Max Activating Token Index: 1001

Text #13

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1985. Min Act: -0.0000

Data Index: 83737 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1606. Min Act: -0.0000

Data Index: 309452 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1792. Min Act: -0.0000

Data Index: 769646 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1705. Min Act: -0.0001

Data Index: 1021198 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1874. Min Act: -0.0001

Data Index: 475650 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1159. Min Act: -0.0001

Data Index: 461407 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1451. Min Act: -0.0000

Data Index: 169052 (C4 (Web Text))

Max Activating Token Index: 539