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

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

Neuron 434 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.8973. Min Act: -0.0000

Data Index: 1552360 (Python Code)

Max Activating Token Index: 652

Text #1

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.6698. Min Act: -0.0000

Data Index: 1584095 (Python Code)

Max Activating Token Index: 989

Text #2

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.6345. Min Act: -0.0000

Data Index: 1558332 (Python Code)

Max Activating Token Index: 630

Text #3

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.7109. Min Act: -0.0000

Data Index: 1393920 (Python Code)

Max Activating Token Index: 305

Text #4

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.6367. Min Act: -0.0000

Data Index: 1403260 (Python Code)

Max Activating Token Index: 502

Text #5

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.5923. Min Act: -0.0000

Data Index: 1448923 (Python Code)

Max Activating Token Index: 112

Text #6

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.5898. Min Act: -0.0000

Data Index: 1604449 (Python Code)

Max Activating Token Index: 1009

Text #7

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.5933. Min Act: -0.0000

Data Index: 1523691 (Python Code)

Max Activating Token Index: 762

Text #8

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.5475. Min Act: -0.0000

Data Index: 1449812 (Python Code)

Max Activating Token Index: 208

Text #9

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.5380. Min Act: -0.0000

Data Index: 1556947 (Python Code)

Max Activating Token Index: 785

Text #10

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.5720. Min Act: -0.0000

Data Index: 1614476 (Python Code)

Max Activating Token Index: 688

Text #11

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.5145. Min Act: 0.0000

Data Index: 1435007 (Python Code)

Max Activating Token Index: 40

Text #12

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.5243. Min Act: -0.0000

Data Index: 1649437 (Python Code)

Max Activating Token Index: 318

Text #13

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.5904. Min Act: -0.0000

Data Index: 1594864 (Python Code)

Max Activating Token Index: 902

Text #14

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.5542. Min Act: -0.0000

Data Index: 1501751 (Python Code)

Max Activating Token Index: 760

Text #15

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.5153. Min Act: -0.0000

Data Index: 1494266 (Python Code)

Max Activating Token Index: 503

Text #16

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.5311. Min Act: -0.0000

Data Index: 1431048 (Python Code)

Max Activating Token Index: 722

Text #17

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1398160 (Python Code)

Max Activating Token Index: 654

Text #18

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.5315. Min Act: -0.0000

Data Index: 1398104 (Python Code)

Max Activating Token Index: 993

Text #19

Max Range: 0.8973. Min Range: -0.8973

Max Act: 0.5598. Min Act: -0.0000

Data Index: 1445777 (Python Code)

Max Activating Token Index: 632