Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1188 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2046. Min Range: -1.2046

Max Act: 1.2046. Min Act: -0.0000

Data Index: 1546916 (Python Code)

Max Activating Token Index: 633

Text #1

Max Range: 1.2046. Min Range: -1.2046

Max Act: 1.0767. Min Act: -0.0000

Data Index: 419999 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.9268. Min Act: -0.0000

Data Index: 329444 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.9847. Min Act: -0.0000

Data Index: 1487470 (Python Code)

Max Activating Token Index: 220

Text #4

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.8921. Min Act: -0.0000

Data Index: 1234516 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.9398. Min Act: -0.0000

Data Index: 622543 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.9002. Min Act: -0.0000

Data Index: 889884 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.8522. Min Act: -0.0000

Data Index: 498519 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.8403. Min Act: -0.0000

Data Index: 1469273 (Python Code)

Max Activating Token Index: 923

Text #9

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1473616 (Python Code)

Max Activating Token Index: 85

Text #10

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7786. Min Act: -0.0000

Data Index: 193083 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.8731. Min Act: -0.0000

Data Index: 1045923 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7817. Min Act: -0.0000

Data Index: 1391820 (Python Code)

Max Activating Token Index: 873

Text #13

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7719. Min Act: -0.0000

Data Index: 1205754 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.6986. Min Act: -0.0000

Data Index: 825086 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7628. Min Act: -0.0000

Data Index: 1504971 (Python Code)

Max Activating Token Index: 313

Text #16

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7281. Min Act: -0.0000

Data Index: 660684 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7567. Min Act: -0.0000

Data Index: 1377491 (Python Code)

Max Activating Token Index: 733

Text #18

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1225323 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 1.2046. Min Range: -1.2046

Max Act: 0.6690. Min Act: -0.0000

Data Index: 61340 (C4 (Web Text))

Max Activating Token Index: 698