Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1319 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.5117. Min Range: -3.5117

Max Act: 3.3964. Min Act: -0.0000

Data Index: 567053 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 3.5117. Min Range: -3.5117

Max Act: 3.5117. Min Act: -0.0000

Data Index: 1148754 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 3.5117. Min Range: -3.5117

Max Act: 3.3839. Min Act: -0.0000

Data Index: 192984 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 3.5117. Min Range: -3.5117

Max Act: 2.4478. Min Act: -0.0000

Data Index: 1052300 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 3.5117. Min Range: -3.5117

Max Act: 1.9309. Min Act: -0.0000

Data Index: 792530 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 3.5117. Min Range: -3.5117

Max Act: 1.8831. Min Act: -0.0000

Data Index: 104975 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 3.5117. Min Range: -3.5117

Max Act: 1.9880. Min Act: -0.0000

Data Index: 1144553 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 3.5117. Min Range: -3.5117

Max Act: 1.8640. Min Act: -0.0000

Data Index: 119810 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 3.5117. Min Range: -3.5117

Max Act: 1.8426. Min Act: -0.0000

Data Index: 272429 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 3.5117. Min Range: -3.5117

Max Act: 1.7468. Min Act: -0.0000

Data Index: 499459 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 3.5117. Min Range: -3.5117

Max Act: 1.6547. Min Act: -0.0000

Data Index: 1068811 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 3.5117. Min Range: -3.5117

Max Act: 1.6339. Min Act: -0.0000

Data Index: 411731 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 3.5117. Min Range: -3.5117

Max Act: 1.7155. Min Act: -0.0000

Data Index: 494733 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 3.5117. Min Range: -3.5117

Max Act: 1.7365. Min Act: -0.0000

Data Index: 1257383 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 3.5117. Min Range: -3.5117

Max Act: 1.6316. Min Act: -0.0000

Data Index: 1133575 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 3.5117. Min Range: -3.5117

Max Act: 1.6565. Min Act: -0.0000

Data Index: 553715 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 3.5117. Min Range: -3.5117

Max Act: 1.5473. Min Act: -0.0000

Data Index: 980942 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 3.5117. Min Range: -3.5117

Max Act: 1.7068. Min Act: -0.0000

Data Index: 158566 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 3.5117. Min Range: -3.5117

Max Act: 1.6714. Min Act: -0.0000

Data Index: 750232 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 3.5117. Min Range: -3.5117

Max Act: 1.5771. Min Act: -0.0000

Data Index: 4416 (C4 (Web Text))

Max Activating Token Index: 704