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

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

Neuron 4807 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: 0.8835. Min Range: -0.8835

Max Act: 0.8835. Min Act: -0.0000

Data Index: 1218814 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.8770. Min Act: -0.0000

Data Index: 891399 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.8636. Min Act: -0.0000

Data Index: 106901 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.8576. Min Act: -0.0000

Data Index: 1158240 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.8148. Min Act: -0.0000

Data Index: 716951 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.8435. Min Act: -0.0000

Data Index: 479859 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.8450. Min Act: -0.0000

Data Index: 704001 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7813. Min Act: -0.0000

Data Index: 385030 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7818. Min Act: -0.0000

Data Index: 821758 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7783. Min Act: -0.0000

Data Index: 1056844 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7541. Min Act: -0.0000

Data Index: 387259 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.8250. Min Act: -0.0000

Data Index: 1115714 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7632. Min Act: -0.0000

Data Index: 1008817 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7577. Min Act: -0.0000

Data Index: 798863 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7339. Min Act: -0.0000

Data Index: 431713 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7235. Min Act: -0.0000

Data Index: 1001514 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.6702. Min Act: -0.0000

Data Index: 489444 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7325. Min Act: -0.0000

Data Index: 25951 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7294. Min Act: -0.0000

Data Index: 18436 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 0.8835. Min Range: -0.8835

Max Act: 0.7463. Min Act: -0.0000

Data Index: 1055091 (C4 (Web Text))

Max Activating Token Index: 763