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

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

Neuron 1162 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.9297. Min Act: -0.0000

Data Index: 238826 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.9140. Min Act: -0.0000

Data Index: 1487963 (Python Code)

Max Activating Token Index: 258

Text #2

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.8761. Min Act: -0.0000

Data Index: 10298 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.8738. Min Act: -0.0000

Data Index: 1428631 (Python Code)

Max Activating Token Index: 116

Text #4

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.8038. Min Act: -0.0000

Data Index: 1426571 (Python Code)

Max Activating Token Index: 107

Text #5

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.8226. Min Act: -0.0000

Data Index: 656385 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.7732. Min Act: -0.0000

Data Index: 1476115 (Python Code)

Max Activating Token Index: 181

Text #7

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.7897. Min Act: -0.0000

Data Index: 1642455 (Python Code)

Max Activating Token Index: 491

Text #8

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.7093. Min Act: -0.0000

Data Index: 1205561 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.7824. Min Act: -0.0000

Data Index: 1357957 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.7573. Min Act: -0.0000

Data Index: 1058754 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.7326. Min Act: -0.0000

Data Index: 1298599 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.7899. Min Act: -0.0000

Data Index: 702907 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.7628. Min Act: -0.0000

Data Index: 740089 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.7449. Min Act: -0.0000

Data Index: 295984 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.7542. Min Act: -0.0000

Data Index: 1614273 (Python Code)

Max Activating Token Index: 615

Text #16

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.7206. Min Act: -0.0000

Data Index: 1555509 (Python Code)

Max Activating Token Index: 531

Text #17

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.7200. Min Act: -0.0000

Data Index: 827550 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6948. Min Act: -0.0000

Data Index: 739943 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.7127. Min Act: -0.0000

Data Index: 1212109 (C4 (Web Text))

Max Activating Token Index: 966