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

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

Neuron 2835 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.6041. Min Act: -0.0000

Data Index: 703118 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.5443. Min Act: -0.0000

Data Index: 1624288 (Python Code)

Max Activating Token Index: 875

Text #2

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.4866. Min Act: 0.0000

Data Index: 1427001 (Python Code)

Max Activating Token Index: 841

Text #3

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.4824. Min Act: -0.0000

Data Index: 676266 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.4498. Min Act: -0.0000

Data Index: 1643324 (Python Code)

Max Activating Token Index: 120

Text #5

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.4892. Min Act: -0.0000

Data Index: 1365088 (Python Code)

Max Activating Token Index: 758

Text #6

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.3854. Min Act: -0.0000

Data Index: 1599491 (Python Code)

Max Activating Token Index: 556

Text #7

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.4063. Min Act: -0.0000

Data Index: 1362147 (Python Code)

Max Activating Token Index: 397

Text #8

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.3806. Min Act: -0.0000

Data Index: 621917 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.3394. Min Act: 0.0001

Data Index: 1498345 (Python Code)

Max Activating Token Index: 563

Text #10

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.3503. Min Act: 0.0000

Data Index: 1380832 (Python Code)

Max Activating Token Index: 373

Text #11

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.3712. Min Act: -0.0000

Data Index: 1647969 (Python Code)

Max Activating Token Index: 431

Text #12

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.3472. Min Act: -0.0000

Data Index: 1409788 (Python Code)

Max Activating Token Index: 356

Text #13

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.3157. Min Act: -0.0000

Data Index: 934375 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.3251. Min Act: -0.0000

Data Index: 1502939 (Python Code)

Max Activating Token Index: 901

Text #15

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.3246. Min Act: -0.0000

Data Index: 1398126 (Python Code)

Max Activating Token Index: 753

Text #16

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1511770 (Python Code)

Max Activating Token Index: 981

Text #17

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.3292. Min Act: -0.0000

Data Index: 1522020 (Python Code)

Max Activating Token Index: 410

Text #18

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.3064. Min Act: -0.0000

Data Index: 1562137 (Python Code)

Max Activating Token Index: 355

Text #19

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.3085. Min Act: 0.0000

Data Index: 1609865 (Python Code)

Max Activating Token Index: 745