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

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

Neuron 1409 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.7564. Min Act: -0.0001

Data Index: 1609652 (Python Code)

Max Activating Token Index: 380

Text #1

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.7726. Min Act: -0.0001

Data Index: 1523306 (Python Code)

Max Activating Token Index: 961

Text #2

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.4893. Min Act: -0.0001

Data Index: 1457544 (Python Code)

Max Activating Token Index: 371

Text #3

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.4917. Min Act: -0.0001

Data Index: 725585 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.5059. Min Act: -0.0001

Data Index: 1508808 (Python Code)

Max Activating Token Index: 785

Text #5

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.5001. Min Act: -0.0001

Data Index: 444136 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.4399. Min Act: -0.0000

Data Index: 1526124 (Python Code)

Max Activating Token Index: 624

Text #7

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.3616. Min Act: -0.0001

Data Index: 1489447 (Python Code)

Max Activating Token Index: 102

Text #8

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.3108. Min Act: -0.0000

Data Index: 1401311 (Python Code)

Max Activating Token Index: 613

Text #9

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.2377. Min Act: -0.0000

Data Index: 1560151 (Python Code)

Max Activating Token Index: 199

Text #10

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.4269. Min Act: -0.0000

Data Index: 1440193 (Python Code)

Max Activating Token Index: 309

Text #11

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.3043. Min Act: -0.0001

Data Index: 1158978 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.1824. Min Act: -0.0001

Data Index: 1655444 (Python Code)

Max Activating Token Index: 220

Text #13

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.2370. Min Act: -0.0000

Data Index: 1426563 (Python Code)

Max Activating Token Index: 964

Text #14

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.2050. Min Act: -0.0000

Data Index: 1483827 (Python Code)

Max Activating Token Index: 467

Text #15

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.1140. Min Act: -0.0000

Data Index: 133797 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 1.7726. Min Range: -1.7726

Max Act: 0.9951. Min Act: -0.0000

Data Index: 1388915 (Python Code)

Max Activating Token Index: 652

Text #17

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.1062. Min Act: -0.0001

Data Index: 920708 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.0526. Min Act: -0.0001

Data Index: 1042289 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 1.7726. Min Range: -1.7726

Max Act: 1.1231. Min Act: -0.0001

Data Index: 1505171 (Python Code)

Max Activating Token Index: 443