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

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

Neuron 4094 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: 0.8876. Min Range: -0.8876

Max Act: 0.8876. Min Act: -0.0000

Data Index: 709575 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.8160. Min Act: -0.0000

Data Index: 806110 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7534. Min Act: -0.0000

Data Index: 351824 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7967. Min Act: -0.0000

Data Index: 1308618 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7567. Min Act: -0.0000

Data Index: 1245859 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7689. Min Act: -0.0000

Data Index: 757523 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.6852. Min Act: -0.0000

Data Index: 372543 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7233. Min Act: -0.0000

Data Index: 613784 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7176. Min Act: -0.0000

Data Index: 1401089 (Python Code)

Max Activating Token Index: 584

Text #9

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.6626. Min Act: -0.0000

Data Index: 125807 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.6955. Min Act: -0.0000

Data Index: 1175205 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.6443. Min Act: -0.0000

Data Index: 1189233 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.6553. Min Act: -0.0000

Data Index: 1339952 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.6765. Min Act: -0.0000

Data Index: 1281999 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.6348. Min Act: -0.0000

Data Index: 567739 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.7076. Min Act: -0.0000

Data Index: 785413 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.6507. Min Act: -0.0000

Data Index: 1343007 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.6008. Min Act: -0.0000

Data Index: 1591082 (Python Code)

Max Activating Token Index: 763

Text #18

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.6410. Min Act: -0.0000

Data Index: 1114275 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.8876. Min Range: -0.8876

Max Act: 0.6510. Min Act: -0.0000

Data Index: 1255628 (C4 (Web Text))

Max Activating Token Index: 682