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

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

Neuron 3491 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.3980. Min Act: -0.0000

Data Index: 44632 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.3545. Min Act: -0.0000

Data Index: 1244580 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.3006. Min Act: -0.0000

Data Index: 48531 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.2893. Min Act: -0.0000

Data Index: 976299 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.2579. Min Act: -0.0000

Data Index: 416477 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.2557. Min Act: -0.0000

Data Index: 414081 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.2637. Min Act: -0.0000

Data Index: 1218599 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.2358. Min Act: -0.0000

Data Index: 640219 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.2525. Min Act: -0.0000

Data Index: 762522 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.2435. Min Act: -0.0000

Data Index: 1041088 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.2487. Min Act: -0.0000

Data Index: 552788 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.2449. Min Act: 0.0000

Data Index: 1216816 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.2545. Min Act: -0.0000

Data Index: 534685 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.2542. Min Act: -0.0000

Data Index: 779335 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.2270. Min Act: -0.0000

Data Index: 985261 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.2361. Min Act: -0.0000

Data Index: 764615 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.2290. Min Act: -0.0000

Data Index: 720851 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.2206. Min Act: -0.0000

Data Index: 12726 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.2265. Min Act: -0.0000

Data Index: 976109 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 0.3980. Min Range: -0.3980

Max Act: 0.2259. Min Act: -0.0000

Data Index: 868125 (C4 (Web Text))

Max Activating Token Index: 623