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

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

Neuron 2543 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.7733. Min Act: 0.0001

Data Index: 10860 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.7174. Min Act: -0.0000

Data Index: 619582 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.6974. Min Act: -0.0000

Data Index: 893027 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.6502. Min Act: -0.0000

Data Index: 1034118 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.6078. Min Act: -0.0000

Data Index: 767093 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.6047. Min Act: 0.0001

Data Index: 407314 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.6245. Min Act: 0.0001

Data Index: 154969 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5872. Min Act: -0.0000

Data Index: 275799 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5596. Min Act: -0.0000

Data Index: 548033 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5467. Min Act: 0.0000

Data Index: 1236259 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5502. Min Act: 0.0000

Data Index: 211349 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5036. Min Act: -0.0000

Data Index: 1030751 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5166. Min Act: -0.0000

Data Index: 58653 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5295. Min Act: -0.0000

Data Index: 1109661 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5284. Min Act: -0.0000

Data Index: 427630 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1081823 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5111. Min Act: -0.0000

Data Index: 1081245 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5230. Min Act: -0.0000

Data Index: 152879 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.4865. Min Act: -0.0000

Data Index: 354078 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.7733. Min Range: -0.7733

Max Act: 0.5057. Min Act: 0.0001

Data Index: 1046889 (C4 (Web Text))

Max Activating Token Index: 906