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

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

Neuron 3260 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.5912. Min Act: -0.0000

Data Index: 1054688 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4290. Min Act: -0.0001

Data Index: 53036 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4139. Min Act: -0.0000

Data Index: 201192 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4190. Min Act: -0.0001

Data Index: 166915 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.4002. Min Act: -0.0000

Data Index: 1279737 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.3625. Min Act: -0.0001

Data Index: 483142 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.3734. Min Act: -0.0001

Data Index: 704438 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.3851. Min Act: -0.0000

Data Index: 200228 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.3772. Min Act: -0.0001

Data Index: 114434 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.3793. Min Act: -0.0001

Data Index: 452092 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.3632. Min Act: -0.0001

Data Index: 869998 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.3457. Min Act: -0.0000

Data Index: 387988 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.3615. Min Act: -0.0000

Data Index: 743880 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.3415. Min Act: -0.0001

Data Index: 878326 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.3372. Min Act: -0.0000

Data Index: 379653 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.2982. Min Act: -0.0001

Data Index: 316313 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.3150. Min Act: -0.0000

Data Index: 464627 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.3053. Min Act: -0.0001

Data Index: 226664 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.2985. Min Act: -0.0000

Data Index: 226071 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 0.5912. Min Range: -0.5912

Max Act: 0.2995. Min Act: -0.0000

Data Index: 1218106 (C4 (Web Text))

Max Activating Token Index: 338