Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 920 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.5366. Min Act: -0.0001

Data Index: 1942 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.4844. Min Act: -0.0001

Data Index: 175221 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.5015. Min Act: -0.0001

Data Index: 704656 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.4637. Min Act: -0.0000

Data Index: 652047 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.4467. Min Act: -0.0001

Data Index: 575543 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.4416. Min Act: -0.0001

Data Index: 677399 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.4355. Min Act: -0.0001

Data Index: 233770 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.4399. Min Act: -0.0001

Data Index: 1272221 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.4478. Min Act: -0.0001

Data Index: 1210354 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.4261. Min Act: -0.0001

Data Index: 955182 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.4281. Min Act: -0.0001

Data Index: 560504 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.4047. Min Act: -0.0001

Data Index: 457061 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.4183. Min Act: -0.0001

Data Index: 1021562 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.4193. Min Act: -0.0001

Data Index: 507223 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.4283. Min Act: -0.0001

Data Index: 231344 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.3989. Min Act: -0.0001

Data Index: 214038 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.3979. Min Act: -0.0001

Data Index: 1127901 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.3660. Min Act: -0.0001

Data Index: 1108968 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.4125. Min Act: -0.0001

Data Index: 328225 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.5366. Min Range: -0.5366

Max Act: 0.4010. Min Act: -0.0000

Data Index: 1080465 (C4 (Web Text))

Max Activating Token Index: 844