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

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

Neuron 2036 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.9947. Min Act: -0.0001

Data Index: 694181 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.9523. Min Act: -0.0001

Data Index: 163930 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.9824. Min Act: -0.0001

Data Index: 578814 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.9833. Min Act: -0.0001

Data Index: 1322299 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.9576. Min Act: -0.0001

Data Index: 693421 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.9491. Min Act: -0.0001

Data Index: 1238672 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.9414. Min Act: -0.0001

Data Index: 27989 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.9351. Min Act: -0.0001

Data Index: 98337 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.9242. Min Act: -0.0001

Data Index: 66059 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.9463. Min Act: -0.0001

Data Index: 69705 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.9208. Min Act: -0.0001

Data Index: 1286946 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.9074. Min Act: -0.0001

Data Index: 794544 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.9017. Min Act: -0.0001

Data Index: 837523 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.9039. Min Act: -0.0001

Data Index: 132763 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.9143. Min Act: -0.0001

Data Index: 699348 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.9015. Min Act: -0.0001

Data Index: 155190 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.9023. Min Act: -0.0001

Data Index: 111530 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.8832. Min Act: -0.0001

Data Index: 294365 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.8950. Min Act: -0.0001

Data Index: 384551 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 0.9947. Min Range: -0.9947

Max Act: 0.8977. Min Act: -0.0001

Data Index: 1231987 (C4 (Web Text))

Max Activating Token Index: 579