Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1212 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3367. Min Range: -2.3367

Max Act: 2.3367. Min Act: -0.0000

Data Index: 808910 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 2.3367. Min Range: -2.3367

Max Act: 2.1141. Min Act: -0.0000

Data Index: 402917 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 2.3367. Min Range: -2.3367

Max Act: 2.3304. Min Act: -0.0000

Data Index: 901270 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 2.3367. Min Range: -2.3367

Max Act: 1.9689. Min Act: -0.0000

Data Index: 80422 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 2.3367. Min Range: -2.3367

Max Act: 1.5694. Min Act: -0.0000

Data Index: 1250135 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 2.3367. Min Range: -2.3367

Max Act: 1.5674. Min Act: -0.0000

Data Index: 829130 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 2.3367. Min Range: -2.3367

Max Act: 1.5230. Min Act: -0.0000

Data Index: 215316 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 2.3367. Min Range: -2.3367

Max Act: 1.5046. Min Act: -0.0000

Data Index: 264987 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 2.3367. Min Range: -2.3367

Max Act: 1.4980. Min Act: -0.0000

Data Index: 1319150 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 2.3367. Min Range: -2.3367

Max Act: 1.4215. Min Act: -0.0000

Data Index: 550468 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 2.3367. Min Range: -2.3367

Max Act: 1.3381. Min Act: -0.0000

Data Index: 1184729 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 2.3367. Min Range: -2.3367

Max Act: 1.3419. Min Act: -0.0000

Data Index: 872960 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 2.3367. Min Range: -2.3367

Max Act: 1.2168. Min Act: -0.0000

Data Index: 26079 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 2.3367. Min Range: -2.3367

Max Act: 1.2991. Min Act: -0.0000

Data Index: 988447 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 2.3367. Min Range: -2.3367

Max Act: 1.3638. Min Act: -0.0000

Data Index: 607441 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 2.3367. Min Range: -2.3367

Max Act: 1.2800. Min Act: -0.0000

Data Index: 1325040 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 2.3367. Min Range: -2.3367

Max Act: 1.2699. Min Act: -0.0000

Data Index: 612668 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 2.3367. Min Range: -2.3367

Max Act: 1.3012. Min Act: -0.0000

Data Index: 1123208 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 2.3367. Min Range: -2.3367

Max Act: 1.3290. Min Act: -0.0000

Data Index: 148395 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 2.3367. Min Range: -2.3367

Max Act: 1.2391. Min Act: -0.0000

Data Index: 963547 (C4 (Web Text))

Max Activating Token Index: 739