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

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

Neuron 1286 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: 1.1107. Min Range: -1.1107

Max Act: 1.0958. Min Act: -0.0001

Data Index: 1063062 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 1.1107. Min Range: -1.1107

Max Act: 1.0427. Min Act: -0.0001

Data Index: 960080 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 1.1107. Min Range: -1.1107

Max Act: 1.1107. Min Act: -0.0001

Data Index: 288192 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 1.1107. Min Range: -1.1107

Max Act: 1.0554. Min Act: -0.0001

Data Index: 167391 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 1.1107. Min Range: -1.1107

Max Act: 1.1050. Min Act: -0.0001

Data Index: 1299778 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 1.1107. Min Range: -1.1107

Max Act: 1.0515. Min Act: -0.0001

Data Index: 532329 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 1.1107. Min Range: -1.1107

Max Act: 1.0413. Min Act: -0.0001

Data Index: 657723 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 1.1107. Min Range: -1.1107

Max Act: 1.0275. Min Act: -0.0001

Data Index: 869142 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 1.1107. Min Range: -1.1107

Max Act: 1.0193. Min Act: -0.0001

Data Index: 1269539 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.9472. Min Act: -0.0001

Data Index: 740941 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 1.1107. Min Range: -1.1107

Max Act: 1.0284. Min Act: -0.0001

Data Index: 1107611 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.9686. Min Act: -0.0001

Data Index: 981818 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.9726. Min Act: -0.0001

Data Index: 70758 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.9597. Min Act: -0.0001

Data Index: 769793 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.9612. Min Act: -0.0001

Data Index: 841802 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.9317. Min Act: -0.0001

Data Index: 566542 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.8899. Min Act: -0.0001

Data Index: 1241460 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.9591. Min Act: -0.0001

Data Index: 899408 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.8509. Min Act: -0.0001

Data Index: 1224778 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 1.1107. Min Range: -1.1107

Max Act: 0.9038. Min Act: -0.0001

Data Index: 37651 (C4 (Web Text))

Max Activating Token Index: 848