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

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

Neuron 2116 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.3900. Min Act: -0.0000

Data Index: 323898 (C4 (Web Text))

Max Activating Token Index: 304

Text #1

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.3497. Min Act: -0.0000

Data Index: 319341 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.3260. Min Act: -0.0000

Data Index: 205070 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.3302. Min Act: -0.0001

Data Index: 1179965 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2909. Min Act: -0.0001

Data Index: 780858 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2958. Min Act: -0.0000

Data Index: 243839 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2833. Min Act: -0.0000

Data Index: 490319 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2917. Min Act: -0.0000

Data Index: 250893 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2794. Min Act: -0.0000

Data Index: 693752 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2847. Min Act: -0.0000

Data Index: 1125501 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2630. Min Act: -0.0001

Data Index: 388146 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2548. Min Act: -0.0001

Data Index: 329988 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2535. Min Act: -0.0000

Data Index: 306312 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2544. Min Act: -0.0001

Data Index: 862377 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2519. Min Act: -0.0001

Data Index: 940055 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2500. Min Act: -0.0001

Data Index: 864985 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2375. Min Act: -0.0000

Data Index: 729409 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2268. Min Act: -0.0001

Data Index: 950671 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2190. Min Act: -0.0001

Data Index: 11008 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 0.3900. Min Range: -0.3900

Max Act: 0.2489. Min Act: -0.0000

Data Index: 910973 (C4 (Web Text))

Max Activating Token Index: 844