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

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

Neuron 954 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: 1.9987. Min Range: -1.9987

Max Act: 1.9987. Min Act: -0.0000

Data Index: 424719 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.5019. Min Act: -0.0000

Data Index: 1138834 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.4762. Min Act: -0.0000

Data Index: 1334102 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.5156. Min Act: -0.0000

Data Index: 522483 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.2782. Min Act: -0.0000

Data Index: 625667 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.3381. Min Act: -0.0000

Data Index: 380584 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.3307. Min Act: -0.0000

Data Index: 1125447 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.3058. Min Act: -0.0000

Data Index: 765422 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.2382. Min Act: -0.0000

Data Index: 1066765 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.2231. Min Act: -0.0000

Data Index: 777525 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.2542. Min Act: -0.0000

Data Index: 606450 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.1018. Min Act: -0.0000

Data Index: 751798 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.1690. Min Act: -0.0000

Data Index: 196765 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.0986. Min Act: -0.0000

Data Index: 151874 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.1578. Min Act: -0.0000

Data Index: 1038502 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.1464. Min Act: -0.0000

Data Index: 855717 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.1219. Min Act: -0.0000

Data Index: 840130 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.0315. Min Act: -0.0000

Data Index: 1203983 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.0580. Min Act: -0.0000

Data Index: 661616 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 1.9987. Min Range: -1.9987

Max Act: 1.1255. Min Act: -0.0000

Data Index: 100423 (C4 (Web Text))

Max Activating Token Index: 797