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

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

Neuron 5634 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.2943. Min Act: -0.0000

Data Index: 518197 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.1481. Min Act: -0.0000

Data Index: 484039 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.1737. Min Act: -0.0000

Data Index: 96608 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.1591. Min Act: -0.0000

Data Index: 135300 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.0946. Min Act: -0.0000

Data Index: 38019 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.0823. Min Act: -0.0000

Data Index: 159999 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.1188. Min Act: -0.0000

Data Index: 601762 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.0405. Min Act: -0.0000

Data Index: 436634 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.0402. Min Act: -0.0000

Data Index: 36897 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.0270. Min Act: -0.0000

Data Index: 714630 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.0090. Min Act: -0.0000

Data Index: 1037594 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.9816. Min Act: -0.0000

Data Index: 452950 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.9152. Min Act: -0.0000

Data Index: 397500 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.9605. Min Act: 0.0000

Data Index: 1028235 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.9415. Min Act: -0.0000

Data Index: 1043914 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.8817. Min Act: -0.0000

Data Index: 292131 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.9230. Min Act: -0.0000

Data Index: 619354 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.9780. Min Act: -0.0000

Data Index: 1248195 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.8477. Min Act: -0.0000

Data Index: 590213 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.9569. Min Act: -0.0000

Data Index: 927925 (C4 (Web Text))

Max Activating Token Index: 551