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

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

Neuron 3942 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1026. Min Range: -1.1026

Max Act: 1.1026. Min Act: -0.0001

Data Index: 538757 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.8959. Min Act: -0.0001

Data Index: 402923 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.8638. Min Act: -0.0001

Data Index: 586091 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.8490. Min Act: -0.0001

Data Index: 295446 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.7725. Min Act: -0.0001

Data Index: 299535 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.8712. Min Act: -0.0001

Data Index: 573313 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.8098. Min Act: -0.0001

Data Index: 1040707 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.8154. Min Act: -0.0001

Data Index: 617471 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.7276. Min Act: -0.0001

Data Index: 476245 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.7567. Min Act: -0.0001

Data Index: 1092463 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.7513. Min Act: -0.0001

Data Index: 37026 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.7625. Min Act: -0.0001

Data Index: 965797 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.7628. Min Act: -0.0001

Data Index: 654080 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.7577. Min Act: -0.0001

Data Index: 1336541 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.7860. Min Act: -0.0001

Data Index: 226888 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.7960. Min Act: -0.0001

Data Index: 1091877 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.8521. Min Act: -0.0001

Data Index: 1214465 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.6772. Min Act: -0.0001

Data Index: 15118 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.6975. Min Act: -0.0001

Data Index: 1236747 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 1.1026. Min Range: -1.1026

Max Act: 0.7250. Min Act: -0.0001

Data Index: 413741 (C4 (Web Text))

Max Activating Token Index: 904