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

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

Neuron 2310 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: 5.3336. Min Range: -5.3336

Max Act: 5.2366. Min Act: -0.0000

Data Index: 254671 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 5.3336. Min Range: -5.3336

Max Act: 5.0215. Min Act: -0.0000

Data Index: 454936 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 5.3336. Min Range: -5.3336

Max Act: 5.3000. Min Act: -0.0000

Data Index: 1554020 (Python Code)

Max Activating Token Index: 25

Text #3

Max Range: 5.3336. Min Range: -5.3336

Max Act: 5.0572. Min Act: -0.0000

Data Index: 1624420 (Python Code)

Max Activating Token Index: 31

Text #4

Max Range: 5.3336. Min Range: -5.3336

Max Act: 5.0496. Min Act: -0.0000

Data Index: 1520247 (Python Code)

Max Activating Token Index: 337

Text #5

Max Range: 5.3336. Min Range: -5.3336

Max Act: 5.3174. Min Act: -0.0000

Data Index: 1557529 (Python Code)

Max Activating Token Index: 375

Text #6

Max Range: 5.3336. Min Range: -5.3336

Max Act: 5.3336. Min Act: -0.0000

Data Index: 1504744 (Python Code)

Max Activating Token Index: 159

Text #7

Max Range: 5.3336. Min Range: -5.3336

Max Act: 5.0292. Min Act: -0.0000

Data Index: 1590230 (Python Code)

Max Activating Token Index: 698

Text #8

Max Range: 5.3336. Min Range: -5.3336

Max Act: 4.7370. Min Act: -0.0000

Data Index: 1477818 (Python Code)

Max Activating Token Index: 139

Text #9

Max Range: 5.3336. Min Range: -5.3336

Max Act: 4.7396. Min Act: -0.0000

Data Index: 1519977 (Python Code)

Max Activating Token Index: 231

Text #10

Max Range: 5.3336. Min Range: -5.3336

Max Act: 4.6939. Min Act: -0.0000

Data Index: 1488222 (Python Code)

Max Activating Token Index: 103

Text #11

Max Range: 5.3336. Min Range: -5.3336

Max Act: 4.8475. Min Act: -0.0000

Data Index: 373759 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 5.3336. Min Range: -5.3336

Max Act: 4.6439. Min Act: -0.0000

Data Index: 1605340 (Python Code)

Max Activating Token Index: 22

Text #13

Max Range: 5.3336. Min Range: -5.3336

Max Act: 4.7764. Min Act: -0.0000

Data Index: 1446266 (Python Code)

Max Activating Token Index: 919

Text #14

Max Range: 5.3336. Min Range: -5.3336

Max Act: 4.7791. Min Act: -0.0000

Data Index: 1410437 (Python Code)

Max Activating Token Index: 84

Text #15

Max Range: 5.3336. Min Range: -5.3336

Max Act: 4.5727. Min Act: -0.0000

Data Index: 1165894 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 5.3336. Min Range: -5.3336

Max Act: 4.5545. Min Act: -0.0000

Data Index: 1652704 (Python Code)

Max Activating Token Index: 328

Text #17

Max Range: 5.3336. Min Range: -5.3336

Max Act: 4.5710. Min Act: -0.0000

Data Index: 1415497 (Python Code)

Max Activating Token Index: 359

Text #18

Max Range: 5.3336. Min Range: -5.3336

Max Act: 5.1113. Min Act: -0.0000

Data Index: 1460070 (Python Code)

Max Activating Token Index: 152

Text #19

Max Range: 5.3336. Min Range: -5.3336

Max Act: 4.7032. Min Act: -0.0000

Data Index: 94296 (C4 (Web Text))

Max Activating Token Index: 919