Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4767 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.4922. Min Act: -0.0000

Data Index: 559504 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.4664. Min Act: -0.0000

Data Index: 1224898 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.4455. Min Act: -0.0000

Data Index: 36343 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.4020. Min Act: -0.0000

Data Index: 770673 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.4037. Min Act: -0.0000

Data Index: 467222 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3796. Min Act: -0.0000

Data Index: 943790 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.4067. Min Act: -0.0000

Data Index: 1107536 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3835. Min Act: -0.0000

Data Index: 1121255 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3574. Min Act: -0.0000

Data Index: 711657 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3504. Min Act: -0.0000

Data Index: 718573 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3678. Min Act: -0.0000

Data Index: 1331981 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3761. Min Act: -0.0000

Data Index: 815741 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3602. Min Act: -0.0000

Data Index: 361578 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3432. Min Act: -0.0000

Data Index: 438578 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3758. Min Act: -0.0000

Data Index: 779057 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3427. Min Act: -0.0000

Data Index: 1072534 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3525. Min Act: -0.0000

Data Index: 523092 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3730. Min Act: -0.0000

Data Index: 488946 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3364. Min Act: -0.0000

Data Index: 1033060 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1098480 (C4 (Web Text))

Max Activating Token Index: 778