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

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

Neuron 5608 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: 2.5817. Min Range: -2.5817

Max Act: 2.5817. Min Act: -0.0000

Data Index: 193311 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 2.5817. Min Range: -2.5817

Max Act: 2.2505. Min Act: -0.0000

Data Index: 818188 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 2.5817. Min Range: -2.5817

Max Act: 2.2087. Min Act: -0.0000

Data Index: 963461 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 2.5817. Min Range: -2.5817

Max Act: 2.1658. Min Act: -0.0000

Data Index: 826607 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 2.5817. Min Range: -2.5817

Max Act: 2.1010. Min Act: -0.0000

Data Index: 21789 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 2.5817. Min Range: -2.5817

Max Act: 1.9300. Min Act: -0.0000

Data Index: 916255 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 2.5817. Min Range: -2.5817

Max Act: 1.9284. Min Act: -0.0000

Data Index: 406880 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 2.5817. Min Range: -2.5817

Max Act: 1.8711. Min Act: -0.0000

Data Index: 1078398 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 2.5817. Min Range: -2.5817

Max Act: 1.8550. Min Act: -0.0000

Data Index: 10723 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 2.5817. Min Range: -2.5817

Max Act: 1.8444. Min Act: -0.0000

Data Index: 1104632 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 2.5817. Min Range: -2.5817

Max Act: 1.9406. Min Act: -0.0000

Data Index: 243915 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 2.5817. Min Range: -2.5817

Max Act: 1.8284. Min Act: -0.0000

Data Index: 1637241 (Python Code)

Max Activating Token Index: 479

Text #12

Max Range: 2.5817. Min Range: -2.5817

Max Act: 1.8732. Min Act: -0.0000

Data Index: 322363 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 2.5817. Min Range: -2.5817

Max Act: 1.7603. Min Act: -0.0000

Data Index: 726844 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 2.5817. Min Range: -2.5817

Max Act: 1.6342. Min Act: -0.0000

Data Index: 441045 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 2.5817. Min Range: -2.5817

Max Act: 1.7109. Min Act: -0.0000

Data Index: 168739 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 2.5817. Min Range: -2.5817

Max Act: 1.6975. Min Act: -0.0000

Data Index: 807224 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 2.5817. Min Range: -2.5817

Max Act: 1.5752. Min Act: -0.0000

Data Index: 1420933 (Python Code)

Max Activating Token Index: 960

Text #18

Max Range: 2.5817. Min Range: -2.5817

Max Act: 1.6415. Min Act: -0.0000

Data Index: 716060 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 2.5817. Min Range: -2.5817

Max Act: 1.4752. Min Act: -0.0000

Data Index: 858899 (C4 (Web Text))

Max Activating Token Index: 339