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

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

Neuron 1628 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9875. Min Range: -1.9875

Max Act: 1.9875. Min Act: -0.0002

Data Index: 1235548 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 1.9875. Min Range: -1.9875

Max Act: 1.7858. Min Act: -0.0002

Data Index: 1098388 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 1.9875. Min Range: -1.9875

Max Act: 1.7580. Min Act: -0.0001

Data Index: 852753 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 1.9875. Min Range: -1.9875

Max Act: 1.7095. Min Act: -0.0001

Data Index: 306906 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 1.9875. Min Range: -1.9875

Max Act: 1.6889. Min Act: -0.0002

Data Index: 970943 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 1.9875. Min Range: -1.9875

Max Act: 1.5621. Min Act: -0.0002

Data Index: 827893 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 1.9875. Min Range: -1.9875

Max Act: 1.5202. Min Act: -0.0001

Data Index: 933892 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 1.9875. Min Range: -1.9875

Max Act: 1.5974. Min Act: -0.0001

Data Index: 1089871 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 1.9875. Min Range: -1.9875

Max Act: 1.6157. Min Act: -0.0002

Data Index: 165630 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 1.9875. Min Range: -1.9875

Max Act: 1.7080. Min Act: -0.0002

Data Index: 367048 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 1.9875. Min Range: -1.9875

Max Act: 1.6068. Min Act: -0.0002

Data Index: 1204521 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 1.9875. Min Range: -1.9875

Max Act: 1.4908. Min Act: -0.0001

Data Index: 908351 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 1.9875. Min Range: -1.9875

Max Act: 1.5757. Min Act: -0.0001

Data Index: 237520 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 1.9875. Min Range: -1.9875

Max Act: 1.4361. Min Act: -0.0001

Data Index: 690068 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 1.9875. Min Range: -1.9875

Max Act: 1.5537. Min Act: -0.0001

Data Index: 1250728 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 1.9875. Min Range: -1.9875

Max Act: 1.5364. Min Act: -0.0002

Data Index: 994557 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 1.9875. Min Range: -1.9875

Max Act: 1.4613. Min Act: -0.0002

Data Index: 363416 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 1.9875. Min Range: -1.9875

Max Act: 1.4082. Min Act: -0.0002

Data Index: 450902 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 1.9875. Min Range: -1.9875

Max Act: 1.4019. Min Act: -0.0002

Data Index: 94538 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 1.9875. Min Range: -1.9875

Max Act: 1.3669. Min Act: -0.0002

Data Index: 982636 (C4 (Web Text))

Max Activating Token Index: 763