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

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

Neuron 3608 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: 2.7964. Min Range: -2.7964

Max Act: 2.7964. Min Act: -0.0000

Data Index: 308190 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 2.7964. Min Range: -2.7964

Max Act: 2.3483. Min Act: -0.0000

Data Index: 1242242 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 2.7964. Min Range: -2.7964

Max Act: 2.3090. Min Act: -0.0000

Data Index: 304808 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 2.7964. Min Range: -2.7964

Max Act: 1.9228. Min Act: -0.0000

Data Index: 945400 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 2.7964. Min Range: -2.7964

Max Act: 1.9146. Min Act: -0.0000

Data Index: 989829 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 2.7964. Min Range: -2.7964

Max Act: 2.1368. Min Act: -0.0000

Data Index: 728784 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 2.7964. Min Range: -2.7964

Max Act: 1.7845. Min Act: -0.0000

Data Index: 353421 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 2.7964. Min Range: -2.7964

Max Act: 1.8437. Min Act: -0.0000

Data Index: 1057394 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 2.7964. Min Range: -2.7964

Max Act: 1.7491. Min Act: -0.0000

Data Index: 660304 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 2.7964. Min Range: -2.7964

Max Act: 1.9362. Min Act: -0.0000

Data Index: 132627 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 2.7964. Min Range: -2.7964

Max Act: 1.7128. Min Act: -0.0000

Data Index: 1194478 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 2.7964. Min Range: -2.7964

Max Act: 1.6821. Min Act: -0.0000

Data Index: 917702 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 2.7964. Min Range: -2.7964

Max Act: 1.6825. Min Act: -0.0000

Data Index: 991498 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 2.7964. Min Range: -2.7964

Max Act: 1.7469. Min Act: -0.0000

Data Index: 556510 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 2.7964. Min Range: -2.7964

Max Act: 1.7424. Min Act: -0.0000

Data Index: 983292 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 2.7964. Min Range: -2.7964

Max Act: 1.5581. Min Act: -0.0000

Data Index: 806899 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 2.7964. Min Range: -2.7964

Max Act: 1.5772. Min Act: -0.0000

Data Index: 520001 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 2.7964. Min Range: -2.7964

Max Act: 1.7463. Min Act: -0.0000

Data Index: 1339353 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 2.7964. Min Range: -2.7964

Max Act: 1.5538. Min Act: -0.0000

Data Index: 900777 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 2.7964. Min Range: -2.7964

Max Act: 1.5672. Min Act: -0.0000

Data Index: 338163 (C4 (Web Text))

Max Activating Token Index: 435