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

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

Neuron 2466 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: 0.9209. Min Range: -0.9209

Max Act: 0.9209. Min Act: -0.0000

Data Index: 1204377 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7983. Min Act: -0.0000

Data Index: 389086 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.8138. Min Act: -0.0000

Data Index: 1106479 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.8022. Min Act: 0.0000

Data Index: 607696 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7758. Min Act: -0.0000

Data Index: 756806 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.8265. Min Act: -0.0000

Data Index: 615459 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7527. Min Act: -0.0000

Data Index: 1318518 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7383. Min Act: -0.0000

Data Index: 77062 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7336. Min Act: -0.0000

Data Index: 309883 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7129. Min Act: -0.0000

Data Index: 282588 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7544. Min Act: -0.0000

Data Index: 1281413 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7248. Min Act: -0.0000

Data Index: 41501 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7231. Min Act: -0.0000

Data Index: 1107492 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7450. Min Act: -0.0000

Data Index: 1326411 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7302. Min Act: -0.0000

Data Index: 316752 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7073. Min Act: -0.0000

Data Index: 880563 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.7251. Min Act: -0.0000

Data Index: 442808 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.6794. Min Act: -0.0000

Data Index: 24706 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.6556. Min Act: 0.0000

Data Index: 1187422 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 0.9209. Min Range: -0.9209

Max Act: 0.6936. Min Act: -0.0000

Data Index: 1267833 (C4 (Web Text))

Max Activating Token Index: 949