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

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

Neuron 550 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: 4.5865. Min Range: -4.5865

Max Act: 4.5865. Min Act: -0.0000

Data Index: 81827 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 4.5865. Min Range: -4.5865

Max Act: 3.1737. Min Act: -0.0000

Data Index: 1159132 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 4.5865. Min Range: -4.5865

Max Act: 3.2470. Min Act: -0.0000

Data Index: 84573 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 4.5865. Min Range: -4.5865

Max Act: 3.0571. Min Act: -0.0000

Data Index: 768115 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 4.5865. Min Range: -4.5865

Max Act: 3.2365. Min Act: -0.0000

Data Index: 502291 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 4.5865. Min Range: -4.5865

Max Act: 3.0543. Min Act: -0.0000

Data Index: 156127 (C4 (Web Text))

Max Activating Token Index: 991

Text #6

Max Range: 4.5865. Min Range: -4.5865

Max Act: 3.1544. Min Act: -0.0000

Data Index: 1132604 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 4.5865. Min Range: -4.5865

Max Act: 3.0239. Min Act: 0.0000

Data Index: 406701 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 4.5865. Min Range: -4.5865

Max Act: 2.8763. Min Act: -0.0000

Data Index: 1235641 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 4.5865. Min Range: -4.5865

Max Act: 2.6697. Min Act: -0.0000

Data Index: 611010 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 4.5865. Min Range: -4.5865

Max Act: 2.7880. Min Act: -0.0000

Data Index: 1307094 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 4.5865. Min Range: -4.5865

Max Act: 2.7041. Min Act: -0.0000

Data Index: 588611 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 4.5865. Min Range: -4.5865

Max Act: 2.5465. Min Act: -0.0000

Data Index: 873925 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 4.5865. Min Range: -4.5865

Max Act: 2.6424. Min Act: -0.0000

Data Index: 587698 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 4.5865. Min Range: -4.5865

Max Act: 2.9464. Min Act: -0.0000

Data Index: 793624 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 4.5865. Min Range: -4.5865

Max Act: 2.7697. Min Act: -0.0000

Data Index: 659844 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 4.5865. Min Range: -4.5865

Max Act: 2.7052. Min Act: -0.0000

Data Index: 1005709 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 4.5865. Min Range: -4.5865

Max Act: 2.4520. Min Act: -0.0000

Data Index: 165134 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 4.5865. Min Range: -4.5865

Max Act: 2.5815. Min Act: -0.0000

Data Index: 587337 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 4.5865. Min Range: -4.5865

Max Act: 2.3231. Min Act: 0.0000

Data Index: 480559 (C4 (Web Text))

Max Activating Token Index: 24