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

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

Neuron 5372 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: 1.0585. Min Range: -1.0585

Max Act: 1.0585. Min Act: -0.0000

Data Index: 5805 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.8804. Min Act: -0.0000

Data Index: 6508 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.8713. Min Act: -0.0000

Data Index: 716886 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.8104. Min Act: -0.0000

Data Index: 1015796 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.8097. Min Act: -0.0000

Data Index: 377514 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.7744. Min Act: -0.0000

Data Index: 601411 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.7893. Min Act: -0.0000

Data Index: 251079 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.7613. Min Act: -0.0000

Data Index: 812929 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.7285. Min Act: -0.0000

Data Index: 1020375 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.7319. Min Act: -0.0000

Data Index: 297 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.6836. Min Act: -0.0000

Data Index: 1234618 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.7109. Min Act: -0.0000

Data Index: 998846 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.7031. Min Act: -0.0000

Data Index: 859345 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.7058. Min Act: -0.0000

Data Index: 655780 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.6942. Min Act: -0.0000

Data Index: 372534 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.6861. Min Act: -0.0000

Data Index: 332744 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.7083. Min Act: -0.0000

Data Index: 1045594 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.6946. Min Act: -0.0000

Data Index: 1231924 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.6337. Min Act: -0.0000

Data Index: 465303 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 1.0585. Min Range: -1.0585

Max Act: 0.6707. Min Act: -0.0000

Data Index: 1077417 (C4 (Web Text))

Max Activating Token Index: 250