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

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

Neuron 6064 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.9350. Min Act: 0.0000

Data Index: 1043587 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.8008. Min Act: -0.0000

Data Index: 196612 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.6461. Min Act: -0.0000

Data Index: 904945 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.6827. Min Act: -0.0000

Data Index: 71396 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.7087. Min Act: -0.0000

Data Index: 155899 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.6600. Min Act: -0.0000

Data Index: 1286164 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.7341. Min Act: -0.0000

Data Index: 584179 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.6781. Min Act: -0.0000

Data Index: 367336 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.6276. Min Act: -0.0000

Data Index: 953362 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.6236. Min Act: -0.0000

Data Index: 1253451 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1160674 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.6224. Min Act: -0.0000

Data Index: 585230 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.6156. Min Act: -0.0000

Data Index: 26472 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.6545. Min Act: -0.0000

Data Index: 49416 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.5884. Min Act: -0.0000

Data Index: 1173930 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.5997. Min Act: -0.0000

Data Index: 907180 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.5416. Min Act: -0.0000

Data Index: 8908 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.5749. Min Act: -0.0000

Data Index: 871722 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.5664. Min Act: -0.0000

Data Index: 542011 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.5977. Min Act: -0.0000

Data Index: 525284 (C4 (Web Text))

Max Activating Token Index: 458