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

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

Neuron 663 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.8192. Min Act: -0.0001

Data Index: 524857 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.6881. Min Act: -0.0001

Data Index: 316871 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.7070. Min Act: -0.0001

Data Index: 260725 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.6916. Min Act: -0.0001

Data Index: 682429 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.6436. Min Act: -0.0000

Data Index: 278830 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5887. Min Act: -0.0001

Data Index: 871924 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.6653. Min Act: -0.0001

Data Index: 716128 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.6392. Min Act: -0.0001

Data Index: 1240723 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5805. Min Act: -0.0001

Data Index: 785066 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.6268. Min Act: -0.0001

Data Index: 783131 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5998. Min Act: -0.0000

Data Index: 1230290 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5837. Min Act: -0.0000

Data Index: 919025 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5825. Min Act: -0.0000

Data Index: 232194 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5620. Min Act: -0.0001

Data Index: 708839 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5798. Min Act: -0.0001

Data Index: 970049 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5238. Min Act: -0.0000

Data Index: 838922 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5757. Min Act: -0.0001

Data Index: 1102902 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5532. Min Act: -0.0001

Data Index: 49698 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5420. Min Act: -0.0001

Data Index: 522342 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5747. Min Act: -0.0000

Data Index: 419919 (C4 (Web Text))

Max Activating Token Index: 370