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

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

Neuron 6037 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5764. Min Range: -1.5764

Max Act: 1.5764. Min Act: -0.0001

Data Index: 1279975 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 1.5764. Min Range: -1.5764

Max Act: 0.7000. Min Act: -0.0001

Data Index: 207402 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 1.5764. Min Range: -1.5764

Max Act: 0.9409. Min Act: -0.0001

Data Index: 1452684 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 1.5764. Min Range: -1.5764

Max Act: 1.1052. Min Act: -0.0000

Data Index: 1142125 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 1.5764. Min Range: -1.5764

Max Act: 0.7894. Min Act: -0.0000

Data Index: 582132 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 1.5764. Min Range: -1.5764

Max Act: 0.6146. Min Act: -0.0001

Data Index: 20138 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 1.5764. Min Range: -1.5764

Max Act: 0.8447. Min Act: -0.0001

Data Index: 1349955 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 1.5764. Min Range: -1.5764

Max Act: 0.9181. Min Act: -0.0001

Data Index: 310105 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 1.5764. Min Range: -1.5764

Max Act: 0.6785. Min Act: -0.0001

Data Index: 1594700 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 1.5764. Min Range: -1.5764

Max Act: 0.1737. Min Act: -0.0001

Data Index: 923728 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 1.5764. Min Range: -1.5764

Max Act: 0.6626. Min Act: -0.0000

Data Index: 1384828 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 1.5764. Min Range: -1.5764

Max Act: 0.7452. Min Act: -0.0001

Data Index: 972421 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 1.5764. Min Range: -1.5764

Max Act: 0.6502. Min Act: -0.0000

Data Index: 1605502 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 1.5764. Min Range: -1.5764

Max Act: 0.5003. Min Act: -0.0001

Data Index: 79126 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 1.5764. Min Range: -1.5764

Max Act: 0.6225. Min Act: -0.0000

Data Index: 937141 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 1.5764. Min Range: -1.5764

Max Act: 0.6617. Min Act: -0.0000

Data Index: 1503491 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 1.5764. Min Range: -1.5764

Max Act: 0.7818. Min Act: -0.0001

Data Index: 1262345 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 1.5764. Min Range: -1.5764

Max Act: 0.4996. Min Act: -0.0001

Data Index: 934248 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.5764. Min Range: -1.5764

Max Act: 0.6152. Min Act: -0.0001

Data Index: 765563 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 1.5764. Min Range: -1.5764

Max Act: 0.5355. Min Act: -0.0001

Data Index: 626924 (C4 (Web Text))

Max Activating Token Index: 1023