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

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

Neuron 3181 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: 0.3826. Min Range: -0.3826

Max Act: 0.3826. Min Act: -0.0001

Data Index: 963633 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3517. Min Act: -0.0000

Data Index: 286594 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3760. Min Act: -0.0000

Data Index: 485365 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1207567 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3499. Min Act: -0.0001

Data Index: 638019 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3613. Min Act: -0.0001

Data Index: 834178 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3181. Min Act: -0.0001

Data Index: 1345404 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3633. Min Act: -0.0000

Data Index: 1067743 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3232. Min Act: -0.0000

Data Index: 1018999 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3251. Min Act: -0.0000

Data Index: 978716 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3401. Min Act: -0.0001

Data Index: 110164 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3475. Min Act: -0.0000

Data Index: 1160165 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3208. Min Act: -0.0000

Data Index: 1177602 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.2980. Min Act: -0.0001

Data Index: 536045 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3208. Min Act: -0.0001

Data Index: 1019556 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3106. Min Act: -0.0000

Data Index: 977213 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3067. Min Act: -0.0000

Data Index: 1106624 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.2976. Min Act: -0.0001

Data Index: 51952 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.2949. Min Act: -0.0000

Data Index: 178101 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.2904. Min Act: -0.0000

Data Index: 291239 (C4 (Web Text))

Max Activating Token Index: 717