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

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

Neuron 4138 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: 0.7964. Min Range: -0.7964

Max Act: 0.7802. Min Act: -0.0000

Data Index: 535431 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.6447. Min Act: -0.0000

Data Index: 1050206 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.7964. Min Act: -0.0000

Data Index: 939296 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.7948. Min Act: -0.0000

Data Index: 591978 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.6939. Min Act: -0.0000

Data Index: 124421 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.6462. Min Act: -0.0000

Data Index: 777212 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.6317. Min Act: -0.0000

Data Index: 1171012 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.5204. Min Act: -0.0000

Data Index: 835346 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.5571. Min Act: -0.0000

Data Index: 541854 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.5655. Min Act: -0.0000

Data Index: 75534 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.5535. Min Act: -0.0000

Data Index: 21077 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.5112. Min Act: -0.0000

Data Index: 911388 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.5548. Min Act: -0.0000

Data Index: 677370 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.4336. Min Act: -0.0000

Data Index: 791955 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.4964. Min Act: -0.0000

Data Index: 1121514 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.5101. Min Act: -0.0000

Data Index: 361909 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.4673. Min Act: -0.0000

Data Index: 878150 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.4634. Min Act: -0.0000

Data Index: 1234387 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.4626. Min Act: -0.0000

Data Index: 637416 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 0.7964. Min Range: -0.7964

Max Act: 0.4705. Min Act: -0.0000

Data Index: 164233 (C4 (Web Text))

Max Activating Token Index: 88