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

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

Neuron 5329 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6560. Min Range: -0.6560

Max Act: 0.6560. Min Act: -0.0000

Data Index: 1552548 (Python Code)

Max Activating Token Index: 89

Text #1

Max Range: 0.6560. Min Range: -0.6560

Max Act: 0.6464. Min Act: -0.0000

Data Index: 584657 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.6560. Min Range: -0.6560

Max Act: 0.6155. Min Act: -0.0000

Data Index: 1097290 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 0.6560. Min Range: -0.6560

Max Act: 0.6159. Min Act: -0.0000

Data Index: 1496547 (Python Code)

Max Activating Token Index: 830

Text #4

Max Range: 0.6560. Min Range: -0.6560

Max Act: 0.6112. Min Act: -0.0000

Data Index: 1508503 (Python Code)

Max Activating Token Index: 316

Text #5

Max Range: 0.6560. Min Range: -0.6560

Max Act: 0.5759. Min Act: -0.0000

Data Index: 1471608 (Python Code)

Max Activating Token Index: 566

Text #6

Max Range: 0.6560. Min Range: -0.6560

Max Act: 0.5067. Min Act: -0.0000

Data Index: 1510804 (Python Code)

Max Activating Token Index: 866

Text #7

Max Range: 0.6560. Min Range: -0.6560

Max Act: 0.5610. Min Act: -0.0000

Data Index: 1569293 (Python Code)

Max Activating Token Index: 695

Text #8

Max Range: 0.6560. Min Range: -0.6560

Max Act: 0.5589. Min Act: -0.0000

Data Index: 1441243 (Python Code)

Max Activating Token Index: 57

Text #9

Max Range: 0.6560. Min Range: -0.6560

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1607251 (Python Code)

Max Activating Token Index: 133

Text #10

Max Range: 0.6560. Min Range: -0.6560

Max Act: 0.5749. Min Act: -0.0000

Data Index: 1399715 (Python Code)

Max Activating Token Index: 920

Text #11

Max Range: 0.6560. Min Range: -0.6560

Max Act: 0.5374. Min Act: -0.0000

Data Index: 1574633 (Python Code)

Max Activating Token Index: 486

Text #12

Max Range: 0.6560. Min Range: -0.6560

Max Act: 0.5130. Min Act: -0.0000

Data Index: 17750 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.6560. Min Range: -0.6560

Max Act: 0.5374. Min Act: -0.0000

Data Index: 849176 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.6560. Min Range: -0.6560

Max Act: 0.5153. Min Act: -0.0000

Data Index: 1471697 (Python Code)

Max Activating Token Index: 509

Text #15

Max Range: 0.6560. Min Range: -0.6560

Max Act: 0.4840. Min Act: -0.0000

Data Index: 1626481 (Python Code)

Max Activating Token Index: 896

Text #16

Max Range: 0.6560. Min Range: -0.6560

Max Act: 0.5257. Min Act: -0.0000

Data Index: 1568803 (Python Code)

Max Activating Token Index: 654

Text #17

Max Range: 0.6560. Min Range: -0.6560

Max Act: 0.5234. Min Act: -0.0000

Data Index: 1629596 (Python Code)

Max Activating Token Index: 62

Text #18

Max Range: 0.6560. Min Range: -0.6560

Max Act: 0.4892. Min Act: -0.0000

Data Index: 1656143 (Python Code)

Max Activating Token Index: 748

Text #19

Max Range: 0.6560. Min Range: -0.6560

Max Act: 0.4532. Min Act: -0.0000

Data Index: 1583582 (Python Code)

Max Activating Token Index: 899