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

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

Neuron 4641 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.9952. Min Act: -0.0000

Data Index: 1252353 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.3678. Min Act: -0.0000

Data Index: 887493 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.3288. Min Act: -0.0000

Data Index: 480337 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.1276. Min Act: -0.0000

Data Index: 1243247 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.0981. Min Act: -0.0000

Data Index: 28774 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.0854. Min Act: -0.0000

Data Index: 1210592 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.0715. Min Act: -0.0000

Data Index: 845221 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.0338. Min Act: -0.0000

Data Index: 490781 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.0450. Min Act: -0.0000

Data Index: 1277201 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.0116. Min Act: -0.0000

Data Index: 1187789 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.0298. Min Act: -0.0000

Data Index: 680175 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.1583. Min Act: -0.0000

Data Index: 361038 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 3.9952. Min Range: -3.9952

Max Act: 2.8545. Min Act: -0.0000

Data Index: 4910 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 3.9952. Min Range: -3.9952

Max Act: 2.8498. Min Act: -0.0000

Data Index: 1028955 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 3.9952. Min Range: -3.9952

Max Act: 2.9716. Min Act: -0.0000

Data Index: 982098 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 3.9952. Min Range: -3.9952

Max Act: 2.9554. Min Act: -0.0000

Data Index: 1113527 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 3.9952. Min Range: -3.9952

Max Act: 2.8024. Min Act: -0.0000

Data Index: 122713 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 3.9952. Min Range: -3.9952

Max Act: 3.0771. Min Act: -0.0000

Data Index: 650462 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 3.9952. Min Range: -3.9952

Max Act: 2.9485. Min Act: -0.0000

Data Index: 996202 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 3.9952. Min Range: -3.9952

Max Act: 2.7671. Min Act: -0.0000

Data Index: 94806 (C4 (Web Text))

Max Activating Token Index: 969