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

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

Neuron 4490 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8517. Min Range: -2.8517

Max Act: 2.8517. Min Act: -0.0000

Data Index: 934009 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 2.8517. Min Range: -2.8517

Max Act: 2.2022. Min Act: -0.0000

Data Index: 499752 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 2.8517. Min Range: -2.8517

Max Act: 2.0279. Min Act: -0.0000

Data Index: 691587 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 2.8517. Min Range: -2.8517

Max Act: 1.9890. Min Act: -0.0000

Data Index: 175094 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 2.8517. Min Range: -2.8517

Max Act: 1.8907. Min Act: -0.0000

Data Index: 563281 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 2.8517. Min Range: -2.8517

Max Act: 1.8823. Min Act: -0.0000

Data Index: 24924 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 2.8517. Min Range: -2.8517

Max Act: 1.8563. Min Act: -0.0000

Data Index: 1306535 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 2.8517. Min Range: -2.8517

Max Act: 1.8309. Min Act: -0.0000

Data Index: 963455 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 2.8517. Min Range: -2.8517

Max Act: 1.8388. Min Act: -0.0000

Data Index: 50145 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 2.8517. Min Range: -2.8517

Max Act: 1.8197. Min Act: -0.0000

Data Index: 613864 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 2.8517. Min Range: -2.8517

Max Act: 1.8136. Min Act: -0.0000

Data Index: 58547 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 2.8517. Min Range: -2.8517

Max Act: 1.8135. Min Act: -0.0000

Data Index: 1014496 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 2.8517. Min Range: -2.8517

Max Act: 1.6956. Min Act: -0.0000

Data Index: 911170 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 2.8517. Min Range: -2.8517

Max Act: 1.7541. Min Act: -0.0000

Data Index: 223469 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 2.8517. Min Range: -2.8517

Max Act: 1.7231. Min Act: -0.0000

Data Index: 169201 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 2.8517. Min Range: -2.8517

Max Act: 1.7712. Min Act: -0.0000

Data Index: 64267 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 2.8517. Min Range: -2.8517

Max Act: 1.6450. Min Act: -0.0000

Data Index: 1213054 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 2.8517. Min Range: -2.8517

Max Act: 1.6306. Min Act: -0.0000

Data Index: 667927 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 2.8517. Min Range: -2.8517

Max Act: 1.5340. Min Act: -0.0000

Data Index: 174747 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 2.8517. Min Range: -2.8517

Max Act: 1.6181. Min Act: -0.0000

Data Index: 367758 (C4 (Web Text))

Max Activating Token Index: 250