Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2863 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3659. Min Act: -0.0001

Data Index: 59407 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3633. Min Act: -0.0001

Data Index: 481194 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3658. Min Act: -0.0001

Data Index: 674186 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3325. Min Act: -0.0001

Data Index: 356495 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3579. Min Act: -0.0001

Data Index: 934139 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3272. Min Act: -0.0001

Data Index: 475830 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3115. Min Act: -0.0001

Data Index: 323643 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3132. Min Act: -0.0001

Data Index: 26685 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3040. Min Act: -0.0001

Data Index: 1312134 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2941. Min Act: -0.0001

Data Index: 36250 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3435. Min Act: -0.0001

Data Index: 1235222 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2917. Min Act: -0.0001

Data Index: 798502 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2617. Min Act: -0.0001

Data Index: 1263740 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2960. Min Act: -0.0001

Data Index: 1327335 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3025. Min Act: -0.0001

Data Index: 1006667 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3026. Min Act: -0.0001

Data Index: 478260 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3215. Min Act: -0.0001

Data Index: 726504 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3004. Min Act: -0.0001

Data Index: 328272 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3178. Min Act: -0.0001

Data Index: 78292 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2894. Min Act: -0.0001

Data Index: 1114151 (C4 (Web Text))

Max Activating Token Index: 152