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

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

Neuron 4830 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2434. Min Act: -0.0001

Data Index: 606128 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2787. Min Act: -0.0000

Data Index: 869409 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2559. Min Act: -0.0000

Data Index: 15085 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2568. Min Act: -0.0000

Data Index: 1269608 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2380. Min Act: -0.0001

Data Index: 936275 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2358. Min Act: -0.0000

Data Index: 1096234 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2432. Min Act: -0.0000

Data Index: 740362 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2500. Min Act: -0.0001

Data Index: 77340 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2502. Min Act: -0.0000

Data Index: 403683 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2504. Min Act: -0.0001

Data Index: 310026 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2326. Min Act: -0.0000

Data Index: 922464 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2244. Min Act: -0.0000

Data Index: 215475 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2174. Min Act: -0.0000

Data Index: 1296511 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2363. Min Act: -0.0000

Data Index: 372977 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2142. Min Act: -0.0000

Data Index: 887039 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2369. Min Act: -0.0000

Data Index: 289792 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2054. Min Act: -0.0000

Data Index: 410327 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2498. Min Act: -0.0000

Data Index: 535607 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2055. Min Act: -0.0000

Data Index: 1109001 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 0.2787. Min Range: -0.2787

Max Act: 0.2132. Min Act: -0.0000

Data Index: 321745 (C4 (Web Text))

Max Activating Token Index: 1018