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

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

Neuron 3971 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1497. Min Act: -0.0000

Data Index: 20721 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1587. Min Act: -0.0000

Data Index: 155046 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1538. Min Act: -0.0000

Data Index: 819003 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0968. Min Act: 0.0000

Data Index: 982579 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0936. Min Act: -0.0000

Data Index: 7111 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0918. Min Act: -0.0000

Data Index: 401086 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0960. Min Act: -0.0000

Data Index: 599076 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0814. Min Act: -0.0000

Data Index: 609161 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0877. Min Act: -0.0000

Data Index: 635718 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0831. Min Act: -0.0000

Data Index: 217149 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0864. Min Act: -0.0000

Data Index: 137145 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0872. Min Act: -0.0000

Data Index: 1319231 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0799. Min Act: -0.0000

Data Index: 802575 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0754. Min Act: -0.0000

Data Index: 597587 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0806. Min Act: -0.0000

Data Index: 660244 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0714. Min Act: 0.0000

Data Index: 1060412 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0817. Min Act: -0.0000

Data Index: 1100365 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0787. Min Act: -0.0000

Data Index: 1110850 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0759. Min Act: -0.0000

Data Index: 848166 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.0717. Min Act: -0.0000

Data Index: 91148 (C4 (Web Text))

Max Activating Token Index: 316