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

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

Neuron 4314 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2457. Min Range: -2.2457

Max Act: 2.2457. Min Act: -0.0000

Data Index: 849264 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 2.2457. Min Range: -2.2457

Max Act: 2.0006. Min Act: -0.0000

Data Index: 425263 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 2.2457. Min Range: -2.2457

Max Act: 2.0115. Min Act: -0.0000

Data Index: 293444 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 2.2457. Min Range: -2.2457

Max Act: 2.0731. Min Act: -0.0000

Data Index: 538228 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 2.2457. Min Range: -2.2457

Max Act: 2.0291. Min Act: -0.0000

Data Index: 1267598 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 2.2457. Min Range: -2.2457

Max Act: 1.8605. Min Act: -0.0000

Data Index: 1333037 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 2.2457. Min Range: -2.2457

Max Act: 1.9767. Min Act: -0.0000

Data Index: 1226705 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 2.2457. Min Range: -2.2457

Max Act: 1.7257. Min Act: -0.0000

Data Index: 489646 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 2.2457. Min Range: -2.2457

Max Act: 1.8124. Min Act: -0.0000

Data Index: 616108 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 2.2457. Min Range: -2.2457

Max Act: 1.5670. Min Act: -0.0000

Data Index: 1279625 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 2.2457. Min Range: -2.2457

Max Act: 1.6499. Min Act: -0.0000

Data Index: 91507 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 2.2457. Min Range: -2.2457

Max Act: 1.6376. Min Act: -0.0000

Data Index: 213464 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 2.2457. Min Range: -2.2457

Max Act: 1.6238. Min Act: -0.0000

Data Index: 459870 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 2.2457. Min Range: -2.2457

Max Act: 1.6315. Min Act: -0.0000

Data Index: 300805 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 2.2457. Min Range: -2.2457

Max Act: 1.6187. Min Act: -0.0000

Data Index: 394396 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 2.2457. Min Range: -2.2457

Max Act: 1.6110. Min Act: -0.0000

Data Index: 373415 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 2.2457. Min Range: -2.2457

Max Act: 1.5218. Min Act: -0.0000

Data Index: 143083 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 2.2457. Min Range: -2.2457

Max Act: 1.5934. Min Act: -0.0000

Data Index: 1574407 (Python Code)

Max Activating Token Index: 1000

Text #18

Max Range: 2.2457. Min Range: -2.2457

Max Act: 1.5845. Min Act: -0.0000

Data Index: 104471 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 2.2457. Min Range: -2.2457

Max Act: 1.5656. Min Act: -0.0000

Data Index: 1416375 (Python Code)

Max Activating Token Index: 7