Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3618 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4175. Min Range: -2.4175

Max Act: 2.2779. Min Act: -0.0000

Data Index: 276685 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 2.4175. Min Range: -2.4175

Max Act: 2.4175. Min Act: -0.0000

Data Index: 26209 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 2.4175. Min Range: -2.4175

Max Act: 2.0871. Min Act: -0.0000

Data Index: 453164 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 2.4175. Min Range: -2.4175

Max Act: 2.0424. Min Act: -0.0000

Data Index: 966079 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 2.4175. Min Range: -2.4175

Max Act: 1.9983. Min Act: -0.0000

Data Index: 1097430 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 2.4175. Min Range: -2.4175

Max Act: 1.9832. Min Act: -0.0000

Data Index: 974915 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 2.4175. Min Range: -2.4175

Max Act: 2.1540. Min Act: -0.0000

Data Index: 190106 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 2.4175. Min Range: -2.4175

Max Act: 2.0437. Min Act: -0.0000

Data Index: 1232035 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 2.4175. Min Range: -2.4175

Max Act: 1.9138. Min Act: -0.0000

Data Index: 822307 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 2.4175. Min Range: -2.4175

Max Act: 1.9075. Min Act: -0.0000

Data Index: 1140016 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 2.4175. Min Range: -2.4175

Max Act: 1.9853. Min Act: -0.0000

Data Index: 319507 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 2.4175. Min Range: -2.4175

Max Act: 2.0958. Min Act: -0.0000

Data Index: 1101731 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 2.4175. Min Range: -2.4175

Max Act: 1.9155. Min Act: -0.0000

Data Index: 133468 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 2.4175. Min Range: -2.4175

Max Act: 1.6714. Min Act: -0.0000

Data Index: 571053 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 2.4175. Min Range: -2.4175

Max Act: 1.9345. Min Act: -0.0000

Data Index: 1119941 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 2.4175. Min Range: -2.4175

Max Act: 1.8528. Min Act: -0.0000

Data Index: 1079338 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 2.4175. Min Range: -2.4175

Max Act: 1.7623. Min Act: -0.0001

Data Index: 78648 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 2.4175. Min Range: -2.4175

Max Act: 1.7200. Min Act: -0.0000

Data Index: 579137 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 2.4175. Min Range: -2.4175

Max Act: 1.6730. Min Act: -0.0000

Data Index: 74430 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 2.4175. Min Range: -2.4175

Max Act: 1.6734. Min Act: -0.0000

Data Index: 997893 (C4 (Web Text))

Max Activating Token Index: 974