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

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

Neuron 2398 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6979. Min Range: -0.6979

Max Act: 0.6979. Min Act: -0.0000

Data Index: 111470 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 0.6979. Min Range: -0.6979

Max Act: 0.6543. Min Act: -0.0000

Data Index: 50545 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 0.6979. Min Range: -0.6979

Max Act: 0.5939. Min Act: -0.0000

Data Index: 736736 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 0.6979. Min Range: -0.6979

Max Act: 0.5802. Min Act: -0.0000

Data Index: 60733 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 0.6979. Min Range: -0.6979

Max Act: 0.5748. Min Act: -0.0000

Data Index: 935042 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 0.6979. Min Range: -0.6979

Max Act: 0.5470. Min Act: -0.0000

Data Index: 1135690 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 0.6979. Min Range: -0.6979

Max Act: 0.5711. Min Act: -0.0000

Data Index: 429920 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 0.6979. Min Range: -0.6979

Max Act: 0.5892. Min Act: -0.0000

Data Index: 1276499 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 0.6979. Min Range: -0.6979

Max Act: 0.5412. Min Act: -0.0000

Data Index: 5514 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 0.6979. Min Range: -0.6979

Max Act: 0.5551. Min Act: -0.0000

Data Index: 1070681 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.6979. Min Range: -0.6979

Max Act: 0.5628. Min Act: -0.0000

Data Index: 492814 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 0.6979. Min Range: -0.6979

Max Act: 0.5284. Min Act: -0.0000

Data Index: 672617 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 0.6979. Min Range: -0.6979

Max Act: 0.5048. Min Act: -0.0000

Data Index: 1220145 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 0.6979. Min Range: -0.6979

Max Act: 0.5265. Min Act: -0.0000

Data Index: 945192 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.6979. Min Range: -0.6979

Max Act: 0.5006. Min Act: -0.0000

Data Index: 292204 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.6979. Min Range: -0.6979

Max Act: 0.4993. Min Act: -0.0000

Data Index: 1041924 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.6979. Min Range: -0.6979

Max Act: 0.4980. Min Act: -0.0000

Data Index: 704441 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 0.6979. Min Range: -0.6979

Max Act: 0.5063. Min Act: -0.0000

Data Index: 766057 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 0.6979. Min Range: -0.6979

Max Act: 0.5136. Min Act: -0.0000

Data Index: 359279 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 0.6979. Min Range: -0.6979

Max Act: 0.4814. Min Act: -0.0000

Data Index: 807898 (C4 (Web Text))

Max Activating Token Index: 737