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

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

Neuron 2047 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.3520. Min Act: -0.0001

Data Index: 137632 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.3822. Min Act: -0.0001

Data Index: 294650 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.3531. Min Act: -0.0001

Data Index: 1074364 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.3788. Min Act: -0.0001

Data Index: 114529 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.3643. Min Act: -0.0001

Data Index: 972456 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.3342. Min Act: -0.0001

Data Index: 691030 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.3050. Min Act: -0.0001

Data Index: 567336 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.3388. Min Act: -0.0001

Data Index: 270287 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.3200. Min Act: -0.0001

Data Index: 156511 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.3260. Min Act: -0.0001

Data Index: 634816 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.3421. Min Act: -0.0001

Data Index: 240495 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.3319. Min Act: -0.0001

Data Index: 1018729 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.3209. Min Act: -0.0001

Data Index: 1055593 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.3540. Min Act: -0.0001

Data Index: 546093 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.3238. Min Act: -0.0001

Data Index: 875723 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.3313. Min Act: -0.0001

Data Index: 1230308 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.2967. Min Act: -0.0001

Data Index: 836718 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.3259. Min Act: -0.0001

Data Index: 243868 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.2929. Min Act: -0.0001

Data Index: 710169 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.3822. Min Range: -0.3822

Max Act: 0.2918. Min Act: -0.0001

Data Index: 621077 (C4 (Web Text))

Max Activating Token Index: 479