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

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

Neuron 3877 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0948. Min Range: -2.0948

Max Act: 2.0948. Min Act: -0.0000

Data Index: 1463520 (Python Code)

Max Activating Token Index: 475

Text #1

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.5787. Min Act: -0.0000

Data Index: 1387437 (Python Code)

Max Activating Token Index: 42

Text #2

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.5663. Min Act: -0.0000

Data Index: 1159688 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.5459. Min Act: -0.0000

Data Index: 1386299 (Python Code)

Max Activating Token Index: 78

Text #4

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.5340. Min Act: -0.0000

Data Index: 366876 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.3830. Min Act: -0.0000

Data Index: 633679 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.3086. Min Act: -0.0000

Data Index: 702650 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.2830. Min Act: -0.0000

Data Index: 1415140 (Python Code)

Max Activating Token Index: 971

Text #8

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.2025. Min Act: -0.0000

Data Index: 290062 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.1798. Min Act: -0.0000

Data Index: 839881 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.3307. Min Act: -0.0000

Data Index: 649028 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.2708. Min Act: -0.0000

Data Index: 350821 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.1223. Min Act: -0.0000

Data Index: 1387933 (Python Code)

Max Activating Token Index: 55

Text #13

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.2463. Min Act: -0.0000

Data Index: 319114 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.1590. Min Act: -0.0000

Data Index: 1163505 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.1824. Min Act: -0.0000

Data Index: 1399677 (Python Code)

Max Activating Token Index: 320

Text #16

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.1656. Min Act: -0.0000

Data Index: 1493408 (Python Code)

Max Activating Token Index: 54

Text #17

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.1493. Min Act: -0.0000

Data Index: 1227195 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.2164. Min Act: -0.0000

Data Index: 33321 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 2.0948. Min Range: -2.0948

Max Act: 1.0624. Min Act: -0.0000

Data Index: 1283649 (C4 (Web Text))

Max Activating Token Index: 983