Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2452 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1007774 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3773. Min Act: -0.0001

Data Index: 846745 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3860. Min Act: -0.0001

Data Index: 932711 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3663. Min Act: -0.0001

Data Index: 1041128 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3851. Min Act: -0.0000

Data Index: 262846 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3721. Min Act: -0.0000

Data Index: 288767 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3573. Min Act: -0.0000

Data Index: 578573 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3411. Min Act: -0.0000

Data Index: 702122 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3251. Min Act: -0.0000

Data Index: 1313789 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3360. Min Act: -0.0000

Data Index: 670534 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3210. Min Act: -0.0000

Data Index: 14624 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3331. Min Act: -0.0000

Data Index: 586785 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3323. Min Act: -0.0000

Data Index: 1021743 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3319. Min Act: -0.0000

Data Index: 110607 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3308. Min Act: -0.0000

Data Index: 562501 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3289. Min Act: -0.0001

Data Index: 120150 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3392. Min Act: -0.0001

Data Index: 92405 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3039. Min Act: -0.0000

Data Index: 52054 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3120. Min Act: -0.0000

Data Index: 39654 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3178. Min Act: -0.0000

Data Index: 446808 (C4 (Web Text))

Max Activating Token Index: 867