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

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

Neuron 448 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8057. Min Range: -2.8057

Max Act: 2.3524. Min Act: -0.0000

Data Index: 10017 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 2.8057. Min Range: -2.8057

Max Act: 2.8057. Min Act: -0.0000

Data Index: 1039597 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 2.8057. Min Range: -2.8057

Max Act: 2.5531. Min Act: -0.0000

Data Index: 590575 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 2.8057. Min Range: -2.8057

Max Act: 2.2920. Min Act: -0.0000

Data Index: 626137 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 2.8057. Min Range: -2.8057

Max Act: 2.2606. Min Act: -0.0000

Data Index: 259201 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 2.8057. Min Range: -2.8057

Max Act: 2.2605. Min Act: -0.0000

Data Index: 334746 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 2.8057. Min Range: -2.8057

Max Act: 2.3751. Min Act: -0.0000

Data Index: 651862 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 2.8057. Min Range: -2.8057

Max Act: 2.3183. Min Act: -0.0000

Data Index: 947007 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 2.8057. Min Range: -2.8057

Max Act: 2.0792. Min Act: -0.0000

Data Index: 90011 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 2.8057. Min Range: -2.8057

Max Act: 2.1592. Min Act: -0.0000

Data Index: 602859 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 2.8057. Min Range: -2.8057

Max Act: 2.1777. Min Act: -0.0000

Data Index: 637630 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 2.8057. Min Range: -2.8057

Max Act: 2.1643. Min Act: -0.0000

Data Index: 911400 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 2.8057. Min Range: -2.8057

Max Act: 2.2641. Min Act: -0.0000

Data Index: 1242410 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 2.8057. Min Range: -2.8057

Max Act: 2.0359. Min Act: -0.0000

Data Index: 745604 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 2.8057. Min Range: -2.8057

Max Act: 2.1111. Min Act: -0.0000

Data Index: 104997 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 2.8057. Min Range: -2.8057

Max Act: 2.2157. Min Act: -0.0000

Data Index: 762623 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 2.8057. Min Range: -2.8057

Max Act: 2.1093. Min Act: -0.0000

Data Index: 700592 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 2.8057. Min Range: -2.8057

Max Act: 2.1866. Min Act: -0.0000

Data Index: 221574 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 2.8057. Min Range: -2.8057

Max Act: 1.9754. Min Act: -0.0000

Data Index: 205430 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 2.8057. Min Range: -2.8057

Max Act: 2.0487. Min Act: -0.0000

Data Index: 416461 (C4 (Web Text))

Max Activating Token Index: 319