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

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

Neuron 4782 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0200. Min Range: -3.0200

Max Act: 3.0200. Min Act: -0.0000

Data Index: 1300556 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 3.0200. Min Range: -3.0200

Max Act: 2.5985. Min Act: -0.0000

Data Index: 248098 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 3.0200. Min Range: -3.0200

Max Act: 2.7290. Min Act: -0.0000

Data Index: 669645 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 3.0200. Min Range: -3.0200

Max Act: 2.6037. Min Act: -0.0000

Data Index: 1153193 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 3.0200. Min Range: -3.0200

Max Act: 2.5300. Min Act: -0.0000

Data Index: 846158 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 3.0200. Min Range: -3.0200

Max Act: 2.4468. Min Act: -0.0000

Data Index: 594443 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 3.0200. Min Range: -3.0200

Max Act: 2.5368. Min Act: -0.0000

Data Index: 1034490 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 3.0200. Min Range: -3.0200

Max Act: 2.6409. Min Act: -0.0000

Data Index: 73920 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 3.0200. Min Range: -3.0200

Max Act: 2.3814. Min Act: -0.0000

Data Index: 288878 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 3.0200. Min Range: -3.0200

Max Act: 2.3634. Min Act: -0.0000

Data Index: 696928 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 3.0200. Min Range: -3.0200

Max Act: 2.2079. Min Act: -0.0000

Data Index: 862095 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 3.0200. Min Range: -3.0200

Max Act: 2.2181. Min Act: -0.0000

Data Index: 202346 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 3.0200. Min Range: -3.0200

Max Act: 2.2336. Min Act: -0.0000

Data Index: 105308 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 3.0200. Min Range: -3.0200

Max Act: 2.2336. Min Act: -0.0000

Data Index: 569939 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 3.0200. Min Range: -3.0200

Max Act: 2.2421. Min Act: -0.0000

Data Index: 963405 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 3.0200. Min Range: -3.0200

Max Act: 2.2289. Min Act: -0.0000

Data Index: 1171250 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 3.0200. Min Range: -3.0200

Max Act: 2.1670. Min Act: -0.0000

Data Index: 883824 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 3.0200. Min Range: -3.0200

Max Act: 2.0431. Min Act: -0.0000

Data Index: 524919 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 3.0200. Min Range: -3.0200

Max Act: 2.2173. Min Act: -0.0000

Data Index: 506153 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 3.0200. Min Range: -3.0200

Max Act: 2.1017. Min Act: -0.0000

Data Index: 885225 (C4 (Web Text))

Max Activating Token Index: 663