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

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

Neuron 3089 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.2936. Min Act: -0.0000

Data Index: 747323 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.2849. Min Act: -0.0000

Data Index: 1054517 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.1954. Min Act: -0.0000

Data Index: 1278348 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.1002. Min Act: -0.0000

Data Index: 600567 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.1722. Min Act: -0.0000

Data Index: 239221 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.0880. Min Act: -0.0000

Data Index: 613415 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.1328. Min Act: -0.0000

Data Index: 1060093 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.9957. Min Act: -0.0000

Data Index: 1097150 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.9483. Min Act: -0.0000

Data Index: 1183716 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.9492. Min Act: -0.0000

Data Index: 519130 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.8904. Min Act: -0.0000

Data Index: 970825 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.9958. Min Act: -0.0000

Data Index: 879849 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.8735. Min Act: -0.0000

Data Index: 982610 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.9407. Min Act: -0.0000

Data Index: 190578 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.8419. Min Act: -0.0000

Data Index: 981075 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.8391. Min Act: -0.0000

Data Index: 1201439 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.8905. Min Act: -0.0000

Data Index: 1616 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.8820. Min Act: -0.0000

Data Index: 1233516 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.8620. Min Act: -0.0000

Data Index: 1342526 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.9142. Min Act: -0.0000

Data Index: 263931 (C4 (Web Text))

Max Activating Token Index: 180