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

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

Neuron 467 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4942. Min Act: -0.0000

Data Index: 757016 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4941. Min Act: -0.0001

Data Index: 1269407 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4854. Min Act: -0.0001

Data Index: 1101209 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4709. Min Act: -0.0000

Data Index: 1134584 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4556. Min Act: -0.0001

Data Index: 925760 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4501. Min Act: -0.0001

Data Index: 1319849 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4685. Min Act: -0.0000

Data Index: 975885 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4508. Min Act: -0.0000

Data Index: 607345 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4319. Min Act: -0.0000

Data Index: 875448 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4297. Min Act: -0.0001

Data Index: 900040 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4424. Min Act: -0.0001

Data Index: 553458 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4555. Min Act: -0.0001

Data Index: 1512374 (Python Code)

Max Activating Token Index: 995

Text #12

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4328. Min Act: -0.0001

Data Index: 995870 (C4 (Web Text))

Max Activating Token Index: 789

Text #13

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4327. Min Act: -0.0000

Data Index: 368391 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4289. Min Act: -0.0000

Data Index: 777426 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4193. Min Act: -0.0001

Data Index: 809489 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4393. Min Act: -0.0000

Data Index: 1105928 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4093. Min Act: -0.0000

Data Index: 1129640 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4359. Min Act: -0.0000

Data Index: 734038 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4373. Min Act: -0.0001

Data Index: 716705 (C4 (Web Text))

Max Activating Token Index: 744