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

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

Neuron 5757 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.7964. Min Act: -0.0000

Data Index: 55323 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.4057. Min Act: -0.0000

Data Index: 896636 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.4567. Min Act: -0.0000

Data Index: 33407 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.5417. Min Act: -0.0000

Data Index: 1219622 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.0738. Min Act: -0.0000

Data Index: 1189628 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.3586. Min Act: -0.0000

Data Index: 658289 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.2674. Min Act: -0.0000

Data Index: 968863 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.5007. Min Act: -0.0000

Data Index: 856054 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.3554. Min Act: -0.0000

Data Index: 88567 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.2140. Min Act: -0.0000

Data Index: 144550 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.2418. Min Act: -0.0000

Data Index: 1239831 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.3216. Min Act: -0.0000

Data Index: 724332 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.3220. Min Act: -0.0000

Data Index: 418888 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.2847. Min Act: -0.0000

Data Index: 897625 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.2308. Min Act: -0.0000

Data Index: 988629 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 3.7964. Min Range: -3.7964

Max Act: 2.9390. Min Act: -0.0000

Data Index: 265409 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.3600. Min Act: -0.0000

Data Index: 657414 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 3.7964. Min Range: -3.7964

Max Act: 3.1845. Min Act: -0.0000

Data Index: 1167559 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 3.7964. Min Range: -3.7964

Max Act: 2.8312. Min Act: -0.0000

Data Index: 116749 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 3.7964. Min Range: -3.7964

Max Act: 2.9328. Min Act: -0.0000

Data Index: 1302370 (C4 (Web Text))

Max Activating Token Index: 604