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

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

Neuron 1756 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: 1.1515. Min Range: -1.1515

Max Act: 1.1515. Min Act: -0.0001

Data Index: 751240 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.9551. Min Act: -0.0001

Data Index: 638348 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.8835. Min Act: -0.0001

Data Index: 442385 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.9135. Min Act: -0.0001

Data Index: 330980 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.8536. Min Act: -0.0001

Data Index: 387318 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.8671. Min Act: -0.0001

Data Index: 576833 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.8661. Min Act: -0.0001

Data Index: 851675 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.8217. Min Act: -0.0001

Data Index: 1496502 (Python Code)

Max Activating Token Index: 504

Text #8

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.8337. Min Act: -0.0001

Data Index: 186569 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.8544. Min Act: -0.0001

Data Index: 600522 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.8257. Min Act: -0.0001

Data Index: 730202 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.8144. Min Act: -0.0001

Data Index: 163037 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.8164. Min Act: -0.0001

Data Index: 1121276 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.8254. Min Act: -0.0001

Data Index: 1222822 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.8365. Min Act: -0.0001

Data Index: 963662 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.8528. Min Act: -0.0001

Data Index: 549354 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.7537. Min Act: -0.0001

Data Index: 969188 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.7538. Min Act: -0.0001

Data Index: 402937 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.7995. Min Act: -0.0001

Data Index: 434730 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.7706. Min Act: -0.0001

Data Index: 70229 (C4 (Web Text))

Max Activating Token Index: 470