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

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

Neuron 3498 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: 0.6886. Min Range: -0.6886

Max Act: 0.6886. Min Act: -0.0000

Data Index: 359017 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.5610. Min Act: -0.0000

Data Index: 318664 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.4803. Min Act: -0.0000

Data Index: 631348 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.4409. Min Act: -0.0000

Data Index: 756406 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.4007. Min Act: -0.0000

Data Index: 1050443 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.4255. Min Act: -0.0000

Data Index: 1167855 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.3935. Min Act: -0.0000

Data Index: 305640 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.4078. Min Act: -0.0000

Data Index: 1066874 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.3692. Min Act: -0.0000

Data Index: 506072 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.3575. Min Act: -0.0000

Data Index: 279698 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.3592. Min Act: -0.0000

Data Index: 902517 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.3358. Min Act: -0.0000

Data Index: 29795 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.3453. Min Act: -0.0000

Data Index: 712819 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.3416. Min Act: -0.0000

Data Index: 415748 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.3268. Min Act: -0.0000

Data Index: 635979 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1291719 (C4 (Web Text))

Max Activating Token Index: 339

Text #16

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.3228. Min Act: -0.0000

Data Index: 589644 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.3113. Min Act: -0.0000

Data Index: 46239 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.3113. Min Act: -0.0000

Data Index: 647189 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 0.6886. Min Range: -0.6886

Max Act: 0.2885. Min Act: -0.0000

Data Index: 546964 (C4 (Web Text))

Max Activating Token Index: 716