Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 346 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 6.1468. Min Range: -6.1468

Max Act: 6.1468. Min Act: -0.0001

Data Index: 1412500 (Python Code)

Max Activating Token Index: 25

Text #1

Max Range: 6.1468. Min Range: -6.1468

Max Act: 6.0238. Min Act: -0.0001

Data Index: 1587254 (Python Code)

Max Activating Token Index: 4

Text #2

Max Range: 6.1468. Min Range: -6.1468

Max Act: 5.9496. Min Act: -0.0001

Data Index: 1576659 (Python Code)

Max Activating Token Index: 21

Text #3

Max Range: 6.1468. Min Range: -6.1468

Max Act: 5.8282. Min Act: -0.0001

Data Index: 1496917 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 6.1468. Min Range: -6.1468

Max Act: 5.6089. Min Act: -0.0001

Data Index: 1387424 (Python Code)

Max Activating Token Index: 860

Text #5

Max Range: 6.1468. Min Range: -6.1468

Max Act: 5.7781. Min Act: -0.0001

Data Index: 1493358 (Python Code)

Max Activating Token Index: 17

Text #6

Max Range: 6.1468. Min Range: -6.1468

Max Act: 5.5719. Min Act: -0.0001

Data Index: 1505105 (Python Code)

Max Activating Token Index: 469

Text #7

Max Range: 6.1468. Min Range: -6.1468

Max Act: 5.5453. Min Act: -0.0001

Data Index: 1583753 (Python Code)

Max Activating Token Index: 13

Text #8

Max Range: 6.1468. Min Range: -6.1468

Max Act: 5.4714. Min Act: -0.0001

Data Index: 1470759 (Python Code)

Max Activating Token Index: 17

Text #9

Max Range: 6.1468. Min Range: -6.1468

Max Act: 5.6535. Min Act: -0.0001

Data Index: 1554174 (Python Code)

Max Activating Token Index: 2

Text #10

Max Range: 6.1468. Min Range: -6.1468

Max Act: 5.6368. Min Act: -0.0001

Data Index: 1537969 (Python Code)

Max Activating Token Index: 148

Text #11

Max Range: 6.1468. Min Range: -6.1468

Max Act: 5.6281. Min Act: -0.0001

Data Index: 1532241 (Python Code)

Max Activating Token Index: 2

Text #12

Max Range: 6.1468. Min Range: -6.1468

Max Act: 5.5297. Min Act: -0.0001

Data Index: 1505790 (Python Code)

Max Activating Token Index: 14

Text #13

Max Range: 6.1468. Min Range: -6.1468

Max Act: 5.4626. Min Act: -0.0001

Data Index: 1644850 (Python Code)

Max Activating Token Index: 49

Text #14

Max Range: 6.1468. Min Range: -6.1468

Max Act: 5.4557. Min Act: -0.0001

Data Index: 1610888 (Python Code)

Max Activating Token Index: 3

Text #15

Max Range: 6.1468. Min Range: -6.1468

Max Act: 5.4232. Min Act: -0.0001

Data Index: 1384566 (Python Code)

Max Activating Token Index: 682

Text #16

Max Range: 6.1468. Min Range: -6.1468

Max Act: 5.4181. Min Act: -0.0001

Data Index: 1538403 (Python Code)

Max Activating Token Index: 383

Text #17

Max Range: 6.1468. Min Range: -6.1468

Max Act: 5.4132. Min Act: -0.0001

Data Index: 1560838 (Python Code)

Max Activating Token Index: 18

Text #18

Max Range: 6.1468. Min Range: -6.1468

Max Act: 5.3991. Min Act: -0.0001

Data Index: 1436329 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 6.1468. Min Range: -6.1468

Max Act: 5.3203. Min Act: -0.0001

Data Index: 1637589 (Python Code)

Max Activating Token Index: 38