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

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

Neuron 1305 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.6274. Min Act: -0.0000

Data Index: 983289 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4964. Min Act: -0.0000

Data Index: 1289843 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.5521. Min Act: -0.0000

Data Index: 542966 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4662. Min Act: -0.0001

Data Index: 411002 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.5108. Min Act: -0.0000

Data Index: 633181 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4888. Min Act: -0.0000

Data Index: 604453 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4682. Min Act: -0.0000

Data Index: 1248221 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.5005. Min Act: -0.0001

Data Index: 566532 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4835. Min Act: -0.0000

Data Index: 1228907 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4574. Min Act: -0.0000

Data Index: 860316 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4467. Min Act: -0.0000

Data Index: 350935 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4113. Min Act: -0.0000

Data Index: 231545 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4610. Min Act: -0.0000

Data Index: 469407 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4417. Min Act: -0.0000

Data Index: 971031 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4437. Min Act: -0.0000

Data Index: 1303202 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4841. Min Act: -0.0000

Data Index: 569246 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4868. Min Act: -0.0000

Data Index: 971837 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.3996. Min Act: -0.0000

Data Index: 406175 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4428. Min Act: -0.0001

Data Index: 118832 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4133. Min Act: -0.0001

Data Index: 683646 (C4 (Web Text))

Max Activating Token Index: 425