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

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

Neuron 5934 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4436. Min Range: -0.4436

Max Act: 0.4244. Min Act: -0.0000

Data Index: 807492 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 0.4436. Min Range: -0.4436

Max Act: 0.3955. Min Act: -0.0000

Data Index: 322510 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 0.4436. Min Range: -0.4436

Max Act: 0.4209. Min Act: -0.0000

Data Index: 83906 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 0.4436. Min Range: -0.4436

Max Act: 0.4436. Min Act: -0.0000

Data Index: 184967 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 0.4436. Min Range: -0.4436

Max Act: 0.4065. Min Act: -0.0000

Data Index: 616454 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 0.4436. Min Range: -0.4436

Max Act: 0.4042. Min Act: -0.0001

Data Index: 1110185 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 0.4436. Min Range: -0.4436

Max Act: 0.3717. Min Act: -0.0001

Data Index: 1355081 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.4436. Min Range: -0.4436

Max Act: 0.3860. Min Act: -0.0000

Data Index: 871698 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 0.4436. Min Range: -0.4436

Max Act: 0.4126. Min Act: -0.0000

Data Index: 1234617 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 0.4436. Min Range: -0.4436

Max Act: 0.3916. Min Act: -0.0000

Data Index: 711689 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 0.4436. Min Range: -0.4436

Max Act: 0.4045. Min Act: -0.0001

Data Index: 135628 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 0.4436. Min Range: -0.4436

Max Act: 0.3904. Min Act: -0.0000

Data Index: 661097 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 0.4436. Min Range: -0.4436

Max Act: 0.4039. Min Act: -0.0000

Data Index: 1040707 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 0.4436. Min Range: -0.4436

Max Act: 0.4134. Min Act: -0.0000

Data Index: 105303 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 0.4436. Min Range: -0.4436

Max Act: 0.3959. Min Act: -0.0000

Data Index: 1357083 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 0.4436. Min Range: -0.4436

Max Act: 0.4040. Min Act: -0.0001

Data Index: 439826 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 0.4436. Min Range: -0.4436

Max Act: 0.3918. Min Act: -0.0000

Data Index: 653423 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.4436. Min Range: -0.4436

Max Act: 0.4035. Min Act: -0.0000

Data Index: 81362 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.4436. Min Range: -0.4436

Max Act: 0.3871. Min Act: -0.0001

Data Index: 362065 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.4436. Min Range: -0.4436

Max Act: 0.3734. Min Act: -0.0001

Data Index: 467172 (C4 (Web Text))

Max Activating Token Index: 262