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

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

Neuron 662 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8083. Min Range: -1.8083

Max Act: 1.7975. Min Act: -0.0000

Data Index: 1042890 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 1.8083. Min Range: -1.8083

Max Act: 1.8083. Min Act: -0.0001

Data Index: 450894 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 1.8083. Min Range: -1.8083

Max Act: 1.4653. Min Act: -0.0001

Data Index: 878306 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 1.8083. Min Range: -1.8083

Max Act: 1.4921. Min Act: -0.0001

Data Index: 564819 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 1.8083. Min Range: -1.8083

Max Act: 1.4333. Min Act: -0.0001

Data Index: 1084261 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 1.8083. Min Range: -1.8083

Max Act: 1.4604. Min Act: -0.0001

Data Index: 788318 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 1.8083. Min Range: -1.8083

Max Act: 1.4444. Min Act: -0.0001

Data Index: 452473 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 1.8083. Min Range: -1.8083

Max Act: 1.3958. Min Act: -0.0001

Data Index: 1242920 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 1.8083. Min Range: -1.8083

Max Act: 1.3455. Min Act: -0.0001

Data Index: 1148293 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 1.8083. Min Range: -1.8083

Max Act: 1.4038. Min Act: -0.0001

Data Index: 480200 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 1.8083. Min Range: -1.8083

Max Act: 1.2483. Min Act: -0.0001

Data Index: 728041 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 1.8083. Min Range: -1.8083

Max Act: 1.3558. Min Act: -0.0001

Data Index: 195497 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 1.8083. Min Range: -1.8083

Max Act: 1.3472. Min Act: -0.0001

Data Index: 844754 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 1.8083. Min Range: -1.8083

Max Act: 1.2877. Min Act: -0.0000

Data Index: 876867 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 1.8083. Min Range: -1.8083

Max Act: 1.2516. Min Act: -0.0001

Data Index: 32267 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 1.8083. Min Range: -1.8083

Max Act: 1.3034. Min Act: -0.0000

Data Index: 587846 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 1.8083. Min Range: -1.8083

Max Act: 1.2251. Min Act: -0.0001

Data Index: 739026 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 1.8083. Min Range: -1.8083

Max Act: 1.2142. Min Act: -0.0000

Data Index: 1046286 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 1.8083. Min Range: -1.8083

Max Act: 1.2391. Min Act: -0.0001

Data Index: 481189 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 1.8083. Min Range: -1.8083

Max Act: 1.2068. Min Act: -0.0001

Data Index: 145948 (C4 (Web Text))

Max Activating Token Index: 666