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

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

Neuron 4209 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: 0.3099. Min Range: -0.3099

Max Act: 0.3035. Min Act: -0.0000

Data Index: 1306278 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.3031. Min Act: -0.0000

Data Index: 1139538 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.3005. Min Act: -0.0000

Data Index: 334058 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.3099. Min Act: -0.0000

Data Index: 1061600 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2853. Min Act: -0.0000

Data Index: 385136 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2917. Min Act: -0.0000

Data Index: 14548 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2892. Min Act: -0.0000

Data Index: 508212 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2607. Min Act: -0.0000

Data Index: 185562 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2680. Min Act: -0.0000

Data Index: 173808 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2617. Min Act: -0.0000

Data Index: 480513 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2530. Min Act: -0.0000

Data Index: 880284 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2457. Min Act: -0.0000

Data Index: 693148 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2439. Min Act: -0.0000

Data Index: 336828 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2229. Min Act: -0.0000

Data Index: 648969 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2199. Min Act: -0.0000

Data Index: 1023552 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2141. Min Act: -0.0000

Data Index: 783303 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2102. Min Act: -0.0000

Data Index: 339782 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2157. Min Act: -0.0000

Data Index: 923069 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.2125. Min Act: -0.0000

Data Index: 409410 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.3099. Min Range: -0.3099

Max Act: 0.1969. Min Act: -0.0000

Data Index: 835563 (C4 (Web Text))

Max Activating Token Index: 36