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

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

Neuron 117 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8475. Min Range: -1.8475

Max Act: 1.8147. Min Act: -0.0000

Data Index: 201942 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 1.8475. Min Range: -1.8475

Max Act: 1.7178. Min Act: -0.0000

Data Index: 734480 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 1.8475. Min Range: -1.8475

Max Act: 1.8475. Min Act: -0.0000

Data Index: 1002494 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 1.8475. Min Range: -1.8475

Max Act: 1.6834. Min Act: -0.0000

Data Index: 462180 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 1.8475. Min Range: -1.8475

Max Act: 1.6574. Min Act: -0.0000

Data Index: 752271 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 1.8475. Min Range: -1.8475

Max Act: 1.6292. Min Act: -0.0000

Data Index: 1350242 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 1.8475. Min Range: -1.8475

Max Act: 1.5598. Min Act: -0.0000

Data Index: 1288900 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 1.8475. Min Range: -1.8475

Max Act: 1.5330. Min Act: -0.0000

Data Index: 326218 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 1.8475. Min Range: -1.8475

Max Act: 1.5415. Min Act: -0.0000

Data Index: 1138142 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 1.8475. Min Range: -1.8475

Max Act: 1.4409. Min Act: -0.0000

Data Index: 406395 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 1.8475. Min Range: -1.8475

Max Act: 1.5379. Min Act: -0.0000

Data Index: 730763 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 1.8475. Min Range: -1.8475

Max Act: 1.4447. Min Act: -0.0000

Data Index: 125457 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 1.8475. Min Range: -1.8475

Max Act: 1.4003. Min Act: -0.0000

Data Index: 1066336 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 1.8475. Min Range: -1.8475

Max Act: 1.3176. Min Act: -0.0000

Data Index: 730283 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 1.8475. Min Range: -1.8475

Max Act: 1.3852. Min Act: -0.0000

Data Index: 723362 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 1.8475. Min Range: -1.8475

Max Act: 1.3825. Min Act: -0.0000

Data Index: 1357481 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 1.8475. Min Range: -1.8475

Max Act: 1.3726. Min Act: -0.0000

Data Index: 512442 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 1.8475. Min Range: -1.8475

Max Act: 1.3065. Min Act: -0.0000

Data Index: 302009 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 1.8475. Min Range: -1.8475

Max Act: 1.5110. Min Act: -0.0000

Data Index: 433725 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 1.8475. Min Range: -1.8475

Max Act: 1.3500. Min Act: -0.0000

Data Index: 1214381 (C4 (Web Text))

Max Activating Token Index: 273