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

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

Neuron 4965 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: 0.8722. Min Range: -0.8722

Max Act: 0.7749. Min Act: -0.0000

Data Index: 1181645 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.8722. Min Act: -0.0000

Data Index: 1127198 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.7754. Min Act: -0.0000

Data Index: 528816 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.8173. Min Act: -0.0000

Data Index: 1070729 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6915. Min Act: -0.0000

Data Index: 1145675 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6761. Min Act: -0.0000

Data Index: 1356256 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6645. Min Act: -0.0000

Data Index: 693435 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1301515 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.7403. Min Act: -0.0000

Data Index: 399789 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6850. Min Act: -0.0000

Data Index: 1070257 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6462. Min Act: -0.0000

Data Index: 1302133 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6443. Min Act: -0.0000

Data Index: 199584 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6626. Min Act: -0.0000

Data Index: 1040139 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6577. Min Act: -0.0000

Data Index: 116125 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6569. Min Act: -0.0000

Data Index: 105697 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6499. Min Act: -0.0000

Data Index: 144054 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6439. Min Act: -0.0000

Data Index: 889522 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6888. Min Act: -0.0000

Data Index: 966139 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6669. Min Act: -0.0000

Data Index: 307602 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 0.8722. Min Range: -0.8722

Max Act: 0.6607. Min Act: -0.0000

Data Index: 126683 (C4 (Web Text))

Max Activating Token Index: 729