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

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

Neuron 1213 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: 4.0888. Min Range: -4.0888

Max Act: 4.0888. Min Act: -0.0000

Data Index: 1308958 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 4.0888. Min Range: -4.0888

Max Act: 3.5931. Min Act: -0.0000

Data Index: 675066 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 4.0888. Min Range: -4.0888

Max Act: 2.9116. Min Act: -0.0000

Data Index: 388108 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 4.0888. Min Range: -4.0888

Max Act: 2.9471. Min Act: -0.0000

Data Index: 1446997 (Python Code)

Max Activating Token Index: 949

Text #4

Max Range: 4.0888. Min Range: -4.0888

Max Act: 2.7817. Min Act: -0.0000

Data Index: 827116 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 4.0888. Min Range: -4.0888

Max Act: 2.7956. Min Act: -0.0000

Data Index: 27771 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 4.0888. Min Range: -4.0888

Max Act: 2.7789. Min Act: -0.0000

Data Index: 469793 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 4.0888. Min Range: -4.0888

Max Act: 2.7801. Min Act: -0.0000

Data Index: 1053973 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 4.0888. Min Range: -4.0888

Max Act: 2.8986. Min Act: -0.0000

Data Index: 1285640 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 4.0888. Min Range: -4.0888

Max Act: 2.7343. Min Act: -0.0000

Data Index: 1309782 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 4.0888. Min Range: -4.0888

Max Act: 2.8430. Min Act: -0.0000

Data Index: 1122166 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 4.0888. Min Range: -4.0888

Max Act: 2.7798. Min Act: -0.0000

Data Index: 225600 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 4.0888. Min Range: -4.0888

Max Act: 2.7467. Min Act: -0.0000

Data Index: 736371 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 4.0888. Min Range: -4.0888

Max Act: 2.6000. Min Act: -0.0000

Data Index: 1377947 (Python Code)

Max Activating Token Index: 171

Text #14

Max Range: 4.0888. Min Range: -4.0888

Max Act: 2.5973. Min Act: -0.0000

Data Index: 1572193 (Python Code)

Max Activating Token Index: 862

Text #15

Max Range: 4.0888. Min Range: -4.0888

Max Act: 2.5045. Min Act: -0.0000

Data Index: 400991 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 4.0888. Min Range: -4.0888

Max Act: 2.2356. Min Act: -0.0000

Data Index: 1343260 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 4.0888. Min Range: -4.0888

Max Act: 2.3651. Min Act: -0.0000

Data Index: 611928 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 4.0888. Min Range: -4.0888

Max Act: 2.4418. Min Act: -0.0000

Data Index: 1160276 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 4.0888. Min Range: -4.0888

Max Act: 2.4372. Min Act: -0.0000

Data Index: 235438 (C4 (Web Text))

Max Activating Token Index: 177