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

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

Neuron 5432 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0734. Min Range: -2.0734

Max Act: 2.0734. Min Act: -0.0000

Data Index: 1293181 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.5262. Min Act: -0.0000

Data Index: 1079806 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.5052. Min Act: -0.0000

Data Index: 1021210 (C4 (Web Text))

Max Activating Token Index: 325

Text #3

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.4436. Min Act: -0.0000

Data Index: 207379 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.4217. Min Act: -0.0000

Data Index: 930809 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.5241. Min Act: -0.0000

Data Index: 453045 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.4454. Min Act: 0.0000

Data Index: 149119 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.3575. Min Act: -0.0000

Data Index: 101611 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.4340. Min Act: -0.0000

Data Index: 968518 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.3394. Min Act: -0.0000

Data Index: 1257781 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.3441. Min Act: -0.0000

Data Index: 765312 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.2946. Min Act: -0.0000

Data Index: 1056182 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.2032. Min Act: -0.0000

Data Index: 760409 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.2472. Min Act: -0.0000

Data Index: 301770 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.1570. Min Act: -0.0000

Data Index: 178428 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.1487. Min Act: -0.0000

Data Index: 950608 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.2232. Min Act: -0.0000

Data Index: 562892 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.2871. Min Act: -0.0000

Data Index: 1022351 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.2103. Min Act: -0.0000

Data Index: 1331667 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 2.0734. Min Range: -2.0734

Max Act: 1.1903. Min Act: -0.0000

Data Index: 51737 (C4 (Web Text))

Max Activating Token Index: 184