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

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

Neuron 1660 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: 0.6757. Min Range: -0.6757

Max Act: 0.6757. Min Act: -0.0000

Data Index: 929730 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.5111. Min Act: -0.0000

Data Index: 1210119 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4756. Min Act: -0.0000

Data Index: 295299 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4671. Min Act: -0.0001

Data Index: 15721 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4493. Min Act: -0.0000

Data Index: 1177229 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4303. Min Act: -0.0000

Data Index: 1196392 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4348. Min Act: -0.0000

Data Index: 482581 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4292. Min Act: -0.0000

Data Index: 668267 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4298. Min Act: -0.0001

Data Index: 900131 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4005. Min Act: -0.0001

Data Index: 1192231 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4407. Min Act: -0.0000

Data Index: 667423 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4075. Min Act: -0.0000

Data Index: 347326 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4009. Min Act: -0.0000

Data Index: 932408 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4195. Min Act: -0.0000

Data Index: 472378 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4178. Min Act: -0.0000

Data Index: 1267348 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4166. Min Act: -0.0000

Data Index: 917069 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4191. Min Act: -0.0000

Data Index: 1346503 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4273. Min Act: -0.0000

Data Index: 801044 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.3969. Min Act: -0.0000

Data Index: 1248449 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4240. Min Act: -0.0000

Data Index: 359915 (C4 (Web Text))

Max Activating Token Index: 162