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

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

Neuron 880 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9957. Min Range: -0.9957

Max Act: 0.9957. Min Act: -0.0000

Data Index: 550413 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 0.9957. Min Range: -0.9957

Max Act: 0.8456. Min Act: -0.0000

Data Index: 547969 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 0.9957. Min Range: -0.9957

Max Act: 0.8084. Min Act: -0.0000

Data Index: 1585510 (Python Code)

Max Activating Token Index: 194

Text #3

Max Range: 0.9957. Min Range: -0.9957

Max Act: 0.8245. Min Act: -0.0000

Data Index: 1579887 (Python Code)

Max Activating Token Index: 815

Text #4

Max Range: 0.9957. Min Range: -0.9957

Max Act: 0.7461. Min Act: -0.0000

Data Index: 233365 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 0.9957. Min Range: -0.9957

Max Act: 0.7785. Min Act: -0.0000

Data Index: 1477905 (Python Code)

Max Activating Token Index: 67

Text #6

Max Range: 0.9957. Min Range: -0.9957

Max Act: 0.7946. Min Act: -0.0000

Data Index: 1525243 (Python Code)

Max Activating Token Index: 366

Text #7

Max Range: 0.9957. Min Range: -0.9957

Max Act: 0.7596. Min Act: -0.0000

Data Index: 220484 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 0.9957. Min Range: -0.9957

Max Act: 0.7629. Min Act: -0.0000

Data Index: 1524718 (Python Code)

Max Activating Token Index: 510

Text #9

Max Range: 0.9957. Min Range: -0.9957

Max Act: 0.7188. Min Act: -0.0000

Data Index: 739136 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 0.9957. Min Range: -0.9957

Max Act: 0.6635. Min Act: -0.0000

Data Index: 786023 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 0.9957. Min Range: -0.9957

Max Act: 0.6837. Min Act: -0.0000

Data Index: 163641 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.9957. Min Range: -0.9957

Max Act: 0.7182. Min Act: -0.0000

Data Index: 479431 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 0.9957. Min Range: -0.9957

Max Act: 0.7063. Min Act: -0.0000

Data Index: 991251 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.9957. Min Range: -0.9957

Max Act: 0.6488. Min Act: -0.0000

Data Index: 1479376 (Python Code)

Max Activating Token Index: 795

Text #15

Max Range: 0.9957. Min Range: -0.9957

Max Act: 0.6275. Min Act: -0.0000

Data Index: 598892 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 0.9957. Min Range: -0.9957

Max Act: 0.6000. Min Act: -0.0000

Data Index: 370341 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 0.9957. Min Range: -0.9957

Max Act: 0.6487. Min Act: -0.0000

Data Index: 1262519 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 0.9957. Min Range: -0.9957

Max Act: 0.6117. Min Act: -0.0000

Data Index: 973407 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.9957. Min Range: -0.9957

Max Act: 0.5819. Min Act: -0.0000

Data Index: 302661 (C4 (Web Text))

Max Activating Token Index: 462