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

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

Neuron 4984 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: 1.5872. Min Range: -1.5872

Max Act: 1.5872. Min Act: -0.0000

Data Index: 107791 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 1.5872. Min Range: -1.5872

Max Act: 1.4821. Min Act: -0.0000

Data Index: 779417 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 1.5872. Min Range: -1.5872

Max Act: 1.4600. Min Act: -0.0000

Data Index: 603590 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 1.5872. Min Range: -1.5872

Max Act: 0.8528. Min Act: -0.0000

Data Index: 728554 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 1.5872. Min Range: -1.5872

Max Act: 0.7789. Min Act: -0.0000

Data Index: 1430302 (Python Code)

Max Activating Token Index: 662

Text #5

Max Range: 1.5872. Min Range: -1.5872

Max Act: 0.7487. Min Act: -0.0000

Data Index: 1504158 (Python Code)

Max Activating Token Index: 335

Text #6

Max Range: 1.5872. Min Range: -1.5872

Max Act: 0.7561. Min Act: -0.0000

Data Index: 1532692 (Python Code)

Max Activating Token Index: 456

Text #7

Max Range: 1.5872. Min Range: -1.5872

Max Act: 0.7271. Min Act: -0.0000

Data Index: 1481042 (Python Code)

Max Activating Token Index: 883

Text #8

Max Range: 1.5872. Min Range: -1.5872

Max Act: 0.7322. Min Act: -0.0000

Data Index: 1568876 (Python Code)

Max Activating Token Index: 385

Text #9

Max Range: 1.5872. Min Range: -1.5872

Max Act: 0.7086. Min Act: -0.0000

Data Index: 1394770 (Python Code)

Max Activating Token Index: 924

Text #10

Max Range: 1.5872. Min Range: -1.5872

Max Act: 0.6729. Min Act: -0.0000

Data Index: 1579414 (Python Code)

Max Activating Token Index: 601

Text #11

Max Range: 1.5872. Min Range: -1.5872

Max Act: 0.6626. Min Act: -0.0000

Data Index: 1378251 (Python Code)

Max Activating Token Index: 945

Text #12

Max Range: 1.5872. Min Range: -1.5872

Max Act: 0.6964. Min Act: -0.0000

Data Index: 1553032 (Python Code)

Max Activating Token Index: 713

Text #13

Max Range: 1.5872. Min Range: -1.5872

Max Act: 0.5844. Min Act: -0.0000

Data Index: 1513883 (Python Code)

Max Activating Token Index: 213

Text #14

Max Range: 1.5872. Min Range: -1.5872

Max Act: 0.6423. Min Act: -0.0000

Data Index: 1613533 (Python Code)

Max Activating Token Index: 104

Text #15

Max Range: 1.5872. Min Range: -1.5872

Max Act: 0.6111. Min Act: -0.0000

Data Index: 1378563 (Python Code)

Max Activating Token Index: 111

Text #16

Max Range: 1.5872. Min Range: -1.5872

Max Act: 0.6392. Min Act: -0.0000

Data Index: 1465151 (Python Code)

Max Activating Token Index: 857

Text #17

Max Range: 1.5872. Min Range: -1.5872

Max Act: 0.6203. Min Act: -0.0000

Data Index: 1523709 (Python Code)

Max Activating Token Index: 960

Text #18

Max Range: 1.5872. Min Range: -1.5872

Max Act: 0.6167. Min Act: -0.0000

Data Index: 1646846 (Python Code)

Max Activating Token Index: 230

Text #19

Max Range: 1.5872. Min Range: -1.5872

Max Act: 0.5748. Min Act: -0.0000

Data Index: 1438549 (Python Code)

Max Activating Token Index: 316