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

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

Neuron 2273 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.4520. Min Act: -0.0001

Data Index: 1489248 (Python Code)

Max Activating Token Index: 375

Text #1

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.4124. Min Act: -0.0001

Data Index: 1441776 (Python Code)

Max Activating Token Index: 389

Text #2

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3919. Min Act: -0.0001

Data Index: 1376846 (Python Code)

Max Activating Token Index: 64

Text #3

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3861. Min Act: -0.0001

Data Index: 1119278 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3764. Min Act: -0.0001

Data Index: 1304124 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3521. Min Act: -0.0000

Data Index: 1404251 (Python Code)

Max Activating Token Index: 767

Text #6

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3548. Min Act: -0.0000

Data Index: 452156 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3403. Min Act: -0.0001

Data Index: 172097 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3221. Min Act: -0.0000

Data Index: 1340298 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3249. Min Act: -0.0000

Data Index: 364842 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3307. Min Act: -0.0001

Data Index: 506360 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3180. Min Act: -0.0001

Data Index: 1539110 (Python Code)

Max Activating Token Index: 245

Text #12

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3117. Min Act: -0.0001

Data Index: 1504377 (Python Code)

Max Activating Token Index: 368

Text #13

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3085. Min Act: -0.0001

Data Index: 1427737 (Python Code)

Max Activating Token Index: 945

Text #14

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.2977. Min Act: -0.0001

Data Index: 1542618 (Python Code)

Max Activating Token Index: 660

Text #15

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3048. Min Act: -0.0001

Data Index: 1360092 (Python Code)

Max Activating Token Index: 106

Text #16

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.2959. Min Act: -0.0000

Data Index: 1511868 (Python Code)

Max Activating Token Index: 327

Text #17

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3041. Min Act: -0.0001

Data Index: 1102543 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3003. Min Act: -0.0000

Data Index: 1066506 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.2989. Min Act: -0.0000

Data Index: 201706 (C4 (Web Text))

Max Activating Token Index: 168