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

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

Neuron 3774 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: 4.4345. Min Range: -4.4345

Max Act: 4.4345. Min Act: -0.0000

Data Index: 435985 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 4.4345. Min Range: -4.4345

Max Act: 4.0354. Min Act: -0.0000

Data Index: 1244326 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 4.4345. Min Range: -4.4345

Max Act: 4.1384. Min Act: -0.0000

Data Index: 34217 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 4.4345. Min Range: -4.4345

Max Act: 3.9307. Min Act: -0.0000

Data Index: 108498 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 4.4345. Min Range: -4.4345

Max Act: 3.6598. Min Act: -0.0000

Data Index: 934759 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 4.4345. Min Range: -4.4345

Max Act: 3.6605. Min Act: -0.0000

Data Index: 1138380 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 4.4345. Min Range: -4.4345

Max Act: 3.7823. Min Act: -0.0000

Data Index: 127064 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 4.4345. Min Range: -4.4345

Max Act: 3.6897. Min Act: -0.0000

Data Index: 711820 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 4.4345. Min Range: -4.4345

Max Act: 3.4020. Min Act: -0.0000

Data Index: 31310 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 4.4345. Min Range: -4.4345

Max Act: 2.7902. Min Act: -0.0000

Data Index: 176535 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 4.4345. Min Range: -4.4345

Max Act: 3.5123. Min Act: -0.0000

Data Index: 738853 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 4.4345. Min Range: -4.4345

Max Act: 3.2180. Min Act: -0.0000

Data Index: 688981 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 4.4345. Min Range: -4.4345

Max Act: 3.5304. Min Act: -0.0000

Data Index: 882752 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 4.4345. Min Range: -4.4345

Max Act: 3.5358. Min Act: -0.0000

Data Index: 753882 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 4.4345. Min Range: -4.4345

Max Act: 3.3167. Min Act: -0.0000

Data Index: 457671 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 4.4345. Min Range: -4.4345

Max Act: 3.1794. Min Act: -0.0000

Data Index: 1313230 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 4.4345. Min Range: -4.4345

Max Act: 2.7509. Min Act: -0.0000

Data Index: 1203997 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 4.4345. Min Range: -4.4345

Max Act: 3.5187. Min Act: -0.0000

Data Index: 734127 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 4.4345. Min Range: -4.4345

Max Act: 3.0739. Min Act: -0.0000

Data Index: 1262993 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 4.4345. Min Range: -4.4345

Max Act: 3.4567. Min Act: -0.0000

Data Index: 1151786 (C4 (Web Text))

Max Activating Token Index: 147