Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3261 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.8453. Min Range: -2.8453

Max Act: 2.8453. Min Act: -0.0000

Data Index: 762919 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 2.8453. Min Range: -2.8453

Max Act: 2.1154. Min Act: -0.0000

Data Index: 520310 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 2.8453. Min Range: -2.8453

Max Act: 2.0575. Min Act: -0.0000

Data Index: 584135 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 2.8453. Min Range: -2.8453

Max Act: 1.7557. Min Act: -0.0000

Data Index: 606798 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 2.8453. Min Range: -2.8453

Max Act: 1.7520. Min Act: -0.0000

Data Index: 703740 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 2.8453. Min Range: -2.8453

Max Act: 1.6511. Min Act: -0.0000

Data Index: 1260618 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 2.8453. Min Range: -2.8453

Max Act: 1.9495. Min Act: -0.0000

Data Index: 372535 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 2.8453. Min Range: -2.8453

Max Act: 1.8217. Min Act: -0.0000

Data Index: 425187 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 2.8453. Min Range: -2.8453

Max Act: 1.7814. Min Act: -0.0000

Data Index: 1118237 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 2.8453. Min Range: -2.8453

Max Act: 1.7575. Min Act: -0.0000

Data Index: 321353 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 2.8453. Min Range: -2.8453

Max Act: 1.5787. Min Act: -0.0000

Data Index: 1286641 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 2.8453. Min Range: -2.8453

Max Act: 1.7467. Min Act: -0.0000

Data Index: 603734 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 2.8453. Min Range: -2.8453

Max Act: 1.7468. Min Act: -0.0000

Data Index: 888781 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 2.8453. Min Range: -2.8453

Max Act: 1.7539. Min Act: -0.0000

Data Index: 479859 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 2.8453. Min Range: -2.8453

Max Act: 1.7233. Min Act: -0.0000

Data Index: 767366 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 2.8453. Min Range: -2.8453

Max Act: 1.6320. Min Act: -0.0000

Data Index: 220406 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 2.8453. Min Range: -2.8453

Max Act: 1.8222. Min Act: -0.0000

Data Index: 1123128 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 2.8453. Min Range: -2.8453

Max Act: 1.8189. Min Act: -0.0000

Data Index: 674681 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 2.8453. Min Range: -2.8453

Max Act: 1.7006. Min Act: -0.0000

Data Index: 413422 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 2.8453. Min Range: -2.8453

Max Act: 1.6831. Min Act: -0.0000

Data Index: 550276 (C4 (Web Text))

Max Activating Token Index: 213