Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4398 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.7376. Min Act: -0.0000

Data Index: 1606540 (Python Code)

Max Activating Token Index: 1022

Text #1

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.7622. Min Act: -0.0000

Data Index: 1614202 (Python Code)

Max Activating Token Index: 573

Text #2

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.7024. Min Act: -0.0000

Data Index: 1558979 (Python Code)

Max Activating Token Index: 774

Text #3

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.8935. Min Act: -0.0000

Data Index: 1653139 (Python Code)

Max Activating Token Index: 288

Text #4

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6654. Min Act: -0.0000

Data Index: 1421269 (Python Code)

Max Activating Token Index: 859

Text #5

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.7504. Min Act: -0.0000

Data Index: 1371824 (Python Code)

Max Activating Token Index: 201

Text #6

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.7961. Min Act: -0.0000

Data Index: 1630280 (Python Code)

Max Activating Token Index: 170

Text #7

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.7110. Min Act: -0.0000

Data Index: 1579372 (Python Code)

Max Activating Token Index: 974

Text #8

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.8077. Min Act: -0.0000

Data Index: 1465254 (Python Code)

Max Activating Token Index: 174

Text #9

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6585. Min Act: -0.0000

Data Index: 1466833 (Python Code)

Max Activating Token Index: 986

Text #10

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.7069. Min Act: -0.0000

Data Index: 1479439 (Python Code)

Max Activating Token Index: 32

Text #11

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.7786. Min Act: -0.0000

Data Index: 1519276 (Python Code)

Max Activating Token Index: 676

Text #12

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6810. Min Act: -0.0000

Data Index: 1477566 (Python Code)

Max Activating Token Index: 798

Text #13

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.7001. Min Act: -0.0000

Data Index: 1605761 (Python Code)

Max Activating Token Index: 748

Text #14

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.7241. Min Act: -0.0000

Data Index: 1379318 (Python Code)

Max Activating Token Index: 797

Text #15

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1593444 (Python Code)

Max Activating Token Index: 639

Text #16

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1412548 (Python Code)

Max Activating Token Index: 794

Text #17

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6210. Min Act: -0.0000

Data Index: 1506498 (Python Code)

Max Activating Token Index: 905

Text #18

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6896. Min Act: -0.0000

Data Index: 1485753 (Python Code)

Max Activating Token Index: 98

Text #19

Max Range: 0.8935. Min Range: -0.8935

Max Act: 0.6609. Min Act: -0.0000

Data Index: 1466303 (Python Code)

Max Activating Token Index: 712