Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 360 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4058. Min Range: -0.4058

Max Act: 0.4058. Min Act: -0.0001

Data Index: 601594 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 0.4058. Min Range: -0.4058

Max Act: 0.4052. Min Act: -0.0000

Data Index: 1650448 (Python Code)

Max Activating Token Index: 382

Text #2

Max Range: 0.4058. Min Range: -0.4058

Max Act: 0.3837. Min Act: -0.0001

Data Index: 1568192 (Python Code)

Max Activating Token Index: 265

Text #3

Max Range: 0.4058. Min Range: -0.4058

Max Act: 0.3803. Min Act: -0.0001

Data Index: 1606094 (Python Code)

Max Activating Token Index: 235

Text #4

Max Range: 0.4058. Min Range: -0.4058

Max Act: 0.3628. Min Act: -0.0000

Data Index: 1238461 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 0.4058. Min Range: -0.4058

Max Act: 0.3818. Min Act: -0.0001

Data Index: 1584438 (Python Code)

Max Activating Token Index: 186

Text #6

Max Range: 0.4058. Min Range: -0.4058

Max Act: 0.3753. Min Act: -0.0001

Data Index: 1588630 (Python Code)

Max Activating Token Index: 468

Text #7

Max Range: 0.4058. Min Range: -0.4058

Max Act: 0.3604. Min Act: -0.0001

Data Index: 1509015 (Python Code)

Max Activating Token Index: 229

Text #8

Max Range: 0.4058. Min Range: -0.4058

Max Act: 0.3691. Min Act: -0.0001

Data Index: 1382575 (Python Code)

Max Activating Token Index: 421

Text #9

Max Range: 0.4058. Min Range: -0.4058

Max Act: 0.3551. Min Act: -0.0001

Data Index: 1521247 (Python Code)

Max Activating Token Index: 14

Text #10

Max Range: 0.4058. Min Range: -0.4058

Max Act: 0.3624. Min Act: -0.0001

Data Index: 1592761 (Python Code)

Max Activating Token Index: 1005

Text #11

Max Range: 0.4058. Min Range: -0.4058

Max Act: 0.3440. Min Act: -0.0001

Data Index: 1558690 (Python Code)

Max Activating Token Index: 329

Text #12

Max Range: 0.4058. Min Range: -0.4058

Max Act: 0.3406. Min Act: -0.0001

Data Index: 1541612 (Python Code)

Max Activating Token Index: 19

Text #13

Max Range: 0.4058. Min Range: -0.4058

Max Act: 0.3306. Min Act: -0.0001

Data Index: 1404001 (Python Code)

Max Activating Token Index: 896

Text #14

Max Range: 0.4058. Min Range: -0.4058

Max Act: 0.3191. Min Act: -0.0001

Data Index: 1502096 (Python Code)

Max Activating Token Index: 853

Text #15

Max Range: 0.4058. Min Range: -0.4058

Max Act: 0.3371. Min Act: -0.0000

Data Index: 1524125 (Python Code)

Max Activating Token Index: 248

Text #16

Max Range: 0.4058. Min Range: -0.4058

Max Act: 0.3246. Min Act: -0.0000

Data Index: 1475282 (Python Code)

Max Activating Token Index: 564

Text #17

Max Range: 0.4058. Min Range: -0.4058

Max Act: 0.3203. Min Act: -0.0001

Data Index: 1521163 (Python Code)

Max Activating Token Index: 322

Text #18

Max Range: 0.4058. Min Range: -0.4058

Max Act: 0.3317. Min Act: -0.0000

Data Index: 427107 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 0.4058. Min Range: -0.4058

Max Act: 0.3310. Min Act: -0.0000

Data Index: 987843 (C4 (Web Text))

Max Activating Token Index: 286