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

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

Neuron 2217 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: 0.5076. Min Range: -0.5076

Max Act: 0.4940. Min Act: -0.0001

Data Index: 1049204 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.5076. Min Act: -0.0001

Data Index: 689940 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4819. Min Act: -0.0001

Data Index: 961241 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4734. Min Act: -0.0001

Data Index: 687670 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4679. Min Act: -0.0001

Data Index: 242488 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4229. Min Act: -0.0001

Data Index: 227514 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4680. Min Act: -0.0001

Data Index: 705580 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4364. Min Act: -0.0001

Data Index: 1641639 (Python Code)

Max Activating Token Index: 525

Text #8

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4635. Min Act: -0.0001

Data Index: 963786 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4479. Min Act: -0.0001

Data Index: 826056 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4377. Min Act: -0.0001

Data Index: 427694 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4249. Min Act: -0.0001

Data Index: 374410 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4438. Min Act: -0.0001

Data Index: 222797 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4414. Min Act: -0.0001

Data Index: 571124 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4049. Min Act: -0.0001

Data Index: 3142 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.3995. Min Act: -0.0001

Data Index: 348514 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4411. Min Act: -0.0001

Data Index: 788348 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4113. Min Act: -0.0001

Data Index: 1642371 (Python Code)

Max Activating Token Index: 510

Text #18

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.4191. Min Act: -0.0001

Data Index: 621059 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.5076. Min Range: -0.5076

Max Act: 0.3897. Min Act: -0.0001

Data Index: 891320 (C4 (Web Text))

Max Activating Token Index: 906