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

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

Neuron 1163 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: 3.1536. Min Range: -3.1536

Max Act: 3.1536. Min Act: -0.0000

Data Index: 1105911 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.6440. Min Act: -0.0000

Data Index: 915481 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.7750. Min Act: -0.0000

Data Index: 713308 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.7622. Min Act: -0.0000

Data Index: 1324764 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.5989. Min Act: -0.0000

Data Index: 964776 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.7313. Min Act: -0.0000

Data Index: 372730 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.5585. Min Act: -0.0000

Data Index: 357175 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.4944. Min Act: -0.0000

Data Index: 44475 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.4931. Min Act: -0.0000

Data Index: 177478 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.4739. Min Act: -0.0000

Data Index: 1318036 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.3347. Min Act: -0.0000

Data Index: 1116160 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.5715. Min Act: -0.0000

Data Index: 128555 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.3820. Min Act: -0.0000

Data Index: 1153382 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.3595. Min Act: -0.0000

Data Index: 326244 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.3448. Min Act: -0.0000

Data Index: 77617 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.3161. Min Act: -0.0000

Data Index: 1164958 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.2770. Min Act: -0.0000

Data Index: 163323 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.3520. Min Act: -0.0000

Data Index: 1156441 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.2493. Min Act: -0.0000

Data Index: 83760 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 3.1536. Min Range: -3.1536

Max Act: 2.2394. Min Act: -0.0000

Data Index: 1037126 (C4 (Web Text))

Max Activating Token Index: 940