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

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

Neuron 5720 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.4240. Min Act: -0.0000

Data Index: 93999 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.3997. Min Act: -0.0000

Data Index: 529400 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.2677. Min Act: -0.0000

Data Index: 1209405 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.0661. Min Act: -0.0000

Data Index: 167022 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.1239. Min Act: -0.0000

Data Index: 714154 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.1001. Min Act: -0.0000

Data Index: 14666 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.1527. Min Act: -0.0000

Data Index: 450006 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.0493. Min Act: -0.0000

Data Index: 787937 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.0168. Min Act: -0.0000

Data Index: 523334 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 1.4240. Min Range: -1.4240

Max Act: 0.9958. Min Act: -0.0000

Data Index: 1075806 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 1.4240. Min Range: -1.4240

Max Act: 0.9128. Min Act: -0.0000

Data Index: 852259 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 1.4240. Min Range: -1.4240

Max Act: 1.0265. Min Act: -0.0000

Data Index: 246309 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 1.4240. Min Range: -1.4240

Max Act: 0.9718. Min Act: -0.0000

Data Index: 931364 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 1.4240. Min Range: -1.4240

Max Act: 0.9484. Min Act: -0.0000

Data Index: 948985 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 1.4240. Min Range: -1.4240

Max Act: 0.9485. Min Act: -0.0000

Data Index: 610762 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 1.4240. Min Range: -1.4240

Max Act: 0.9362. Min Act: -0.0000

Data Index: 164116 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 1.4240. Min Range: -1.4240

Max Act: 0.8773. Min Act: -0.0000

Data Index: 296993 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 1.4240. Min Range: -1.4240

Max Act: 0.9007. Min Act: -0.0000

Data Index: 344306 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 1.4240. Min Range: -1.4240

Max Act: 0.8827. Min Act: -0.0000

Data Index: 573243 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 1.4240. Min Range: -1.4240

Max Act: 0.8732. Min Act: -0.0000

Data Index: 809123 (C4 (Web Text))

Max Activating Token Index: 664