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

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

Neuron 4271 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7151. Min Range: -1.7151

Max Act: 1.7151. Min Act: -0.0000

Data Index: 1524781 (Python Code)

Max Activating Token Index: 843

Text #1

Max Range: 1.7151. Min Range: -1.7151

Max Act: 1.2896. Min Act: -0.0000

Data Index: 1471486 (Python Code)

Max Activating Token Index: 626

Text #2

Max Range: 1.7151. Min Range: -1.7151

Max Act: 1.3413. Min Act: -0.0000

Data Index: 592232 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 1.7151. Min Range: -1.7151

Max Act: 1.1030. Min Act: -0.0000

Data Index: 1518595 (Python Code)

Max Activating Token Index: 224

Text #4

Max Range: 1.7151. Min Range: -1.7151

Max Act: 1.1422. Min Act: -0.0000

Data Index: 1577313 (Python Code)

Max Activating Token Index: 536

Text #5

Max Range: 1.7151. Min Range: -1.7151

Max Act: 1.1748. Min Act: -0.0000

Data Index: 884399 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 1.7151. Min Range: -1.7151

Max Act: 1.2556. Min Act: -0.0000

Data Index: 1401569 (Python Code)

Max Activating Token Index: 255

Text #7

Max Range: 1.7151. Min Range: -1.7151

Max Act: 0.9857. Min Act: -0.0000

Data Index: 1462692 (Python Code)

Max Activating Token Index: 105

Text #8

Max Range: 1.7151. Min Range: -1.7151

Max Act: 1.0745. Min Act: -0.0000

Data Index: 1435711 (Python Code)

Max Activating Token Index: 396

Text #9

Max Range: 1.7151. Min Range: -1.7151

Max Act: 1.1204. Min Act: -0.0000

Data Index: 1429528 (Python Code)

Max Activating Token Index: 73

Text #10

Max Range: 1.7151. Min Range: -1.7151

Max Act: 1.1305. Min Act: -0.0000

Data Index: 1617767 (Python Code)

Max Activating Token Index: 112

Text #11

Max Range: 1.7151. Min Range: -1.7151

Max Act: 1.1128. Min Act: -0.0000

Data Index: 209210 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 1.7151. Min Range: -1.7151

Max Act: 1.1224. Min Act: -0.0000

Data Index: 1184948 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 1.7151. Min Range: -1.7151

Max Act: 1.1415. Min Act: -0.0000

Data Index: 1534050 (Python Code)

Max Activating Token Index: 788

Text #14

Max Range: 1.7151. Min Range: -1.7151

Max Act: 1.0391. Min Act: -0.0000

Data Index: 556335 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 1.7151. Min Range: -1.7151

Max Act: 1.0240. Min Act: -0.0000

Data Index: 66379 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 1.7151. Min Range: -1.7151

Max Act: 1.0890. Min Act: -0.0000

Data Index: 804719 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 1.7151. Min Range: -1.7151

Max Act: 1.0792. Min Act: -0.0000

Data Index: 376119 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 1.7151. Min Range: -1.7151

Max Act: 0.9532. Min Act: -0.0000

Data Index: 82803 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 1.7151. Min Range: -1.7151

Max Act: 1.1549. Min Act: -0.0000

Data Index: 1544225 (Python Code)

Max Activating Token Index: 244