Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3265 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.7593. Min Act: -0.0000

Data Index: 98348 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.5402. Min Act: -0.0000

Data Index: 1317785 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.2702. Min Act: -0.0000

Data Index: 930575 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.3348. Min Act: -0.0000

Data Index: 969759 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.3147. Min Act: -0.0000

Data Index: 358072 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.2821. Min Act: -0.0000

Data Index: 281774 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.2453. Min Act: -0.0000

Data Index: 952046 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.2837. Min Act: -0.0000

Data Index: 1325529 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.2528. Min Act: -0.0000

Data Index: 533582 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.2380. Min Act: -0.0000

Data Index: 684738 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.1973. Min Act: -0.0000

Data Index: 313758 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.1964. Min Act: -0.0000

Data Index: 12481 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.2190. Min Act: -0.0000

Data Index: 895265 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.1910. Min Act: -0.0000

Data Index: 387128 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.1896. Min Act: -0.0000

Data Index: 859182 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.1866. Min Act: -0.0000

Data Index: 606070 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 2.7593. Min Range: -2.7593

Max Act: 1.9400. Min Act: -0.0000

Data Index: 1184930 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.1505. Min Act: -0.0000

Data Index: 430412 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.1459. Min Act: -0.0000

Data Index: 968953 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 2.7593. Min Range: -2.7593

Max Act: 2.1178. Min Act: -0.0000

Data Index: 822479 (C4 (Web Text))

Max Activating Token Index: 252