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

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

Neuron 3173 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2645. Min Range: -1.2645

Max Act: 1.2645. Min Act: -0.0001

Data Index: 212499 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 1.2645. Min Range: -1.2645

Max Act: 1.0247. Min Act: -0.0001

Data Index: 790724 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 1.2645. Min Range: -1.2645

Max Act: 1.0085. Min Act: -0.0001

Data Index: 741525 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.9750. Min Act: -0.0001

Data Index: 468463 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.9117. Min Act: -0.0001

Data Index: 95307 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.8946. Min Act: -0.0001

Data Index: 575586 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.9691. Min Act: -0.0001

Data Index: 239421 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.8872. Min Act: -0.0001

Data Index: 513179 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.7235. Min Act: -0.0001

Data Index: 479183 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.8445. Min Act: -0.0001

Data Index: 523111 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.8840. Min Act: -0.0001

Data Index: 1027234 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.8690. Min Act: -0.0001

Data Index: 659008 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.8268. Min Act: -0.0001

Data Index: 1298869 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.8395. Min Act: -0.0001

Data Index: 519838 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.7450. Min Act: -0.0001

Data Index: 1241284 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.7659. Min Act: -0.0001

Data Index: 9075 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.8689. Min Act: -0.0001

Data Index: 419655 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.7613. Min Act: -0.0001

Data Index: 1341305 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.7165. Min Act: -0.0001

Data Index: 98076 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 1.2645. Min Range: -1.2645

Max Act: 0.7305. Min Act: -0.0001

Data Index: 1100472 (C4 (Web Text))

Max Activating Token Index: 138