Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 594 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1027. Min Range: -1.1027

Max Act: 1.1027. Min Act: -0.0001

Data Index: 1037052 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 1.1027. Min Range: -1.1027

Max Act: 1.0258. Min Act: -0.0000

Data Index: 496599 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 1.1027. Min Range: -1.1027

Max Act: 1.0997. Min Act: -0.0000

Data Index: 602302 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 1.1027. Min Range: -1.1027

Max Act: 1.0333. Min Act: -0.0001

Data Index: 142633 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 1.1027. Min Range: -1.1027

Max Act: 1.0447. Min Act: -0.0001

Data Index: 1266009 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 1.1027. Min Range: -1.1027

Max Act: 1.0136. Min Act: 0.0000

Data Index: 1204172 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 1.1027. Min Range: -1.1027

Max Act: 1.0438. Min Act: -0.0000

Data Index: 682384 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.9531. Min Act: -0.0000

Data Index: 59844 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.8983. Min Act: -0.0001

Data Index: 689537 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.9460. Min Act: -0.0000

Data Index: 603535 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.9113. Min Act: -0.0000

Data Index: 772780 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.8497. Min Act: -0.0000

Data Index: 768988 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.8479. Min Act: -0.0000

Data Index: 370893 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.8369. Min Act: -0.0001

Data Index: 1183833 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.8376. Min Act: -0.0000

Data Index: 205578 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.8315. Min Act: -0.0000

Data Index: 41006 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.8565. Min Act: -0.0000

Data Index: 590829 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.7614. Min Act: -0.0000

Data Index: 201953 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.8398. Min Act: -0.0000

Data Index: 211839 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.7831. Min Act: -0.0001

Data Index: 351914 (C4 (Web Text))

Max Activating Token Index: 828