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

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

Neuron 2495 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9997. Min Range: -1.9997

Max Act: 1.9997. Min Act: -0.0000

Data Index: 809276 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 1.9997. Min Range: -1.9997

Max Act: 1.5495. Min Act: -0.0000

Data Index: 94818 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 1.9997. Min Range: -1.9997

Max Act: 1.5896. Min Act: -0.0000

Data Index: 897664 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 1.9997. Min Range: -1.9997

Max Act: 1.5898. Min Act: -0.0000

Data Index: 628155 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 1.9997. Min Range: -1.9997

Max Act: 1.3079. Min Act: -0.0000

Data Index: 796587 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 1.9997. Min Range: -1.9997

Max Act: 1.5034. Min Act: -0.0000

Data Index: 303097 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 1.9997. Min Range: -1.9997

Max Act: 1.4808. Min Act: -0.0000

Data Index: 1278546 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 1.9997. Min Range: -1.9997

Max Act: 1.5155. Min Act: -0.0000

Data Index: 372881 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 1.9997. Min Range: -1.9997

Max Act: 1.3910. Min Act: -0.0000

Data Index: 1258094 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 1.9997. Min Range: -1.9997

Max Act: 1.3739. Min Act: -0.0000

Data Index: 412844 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 1.9997. Min Range: -1.9997

Max Act: 1.4171. Min Act: -0.0000

Data Index: 1192425 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 1.9997. Min Range: -1.9997

Max Act: 1.4830. Min Act: -0.0000

Data Index: 7750 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 1.9997. Min Range: -1.9997

Max Act: 1.4434. Min Act: -0.0000

Data Index: 340523 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 1.9997. Min Range: -1.9997

Max Act: 1.3542. Min Act: -0.0000

Data Index: 588563 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 1.9997. Min Range: -1.9997

Max Act: 1.4366. Min Act: -0.0000

Data Index: 212323 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 1.9997. Min Range: -1.9997

Max Act: 1.5069. Min Act: -0.0000

Data Index: 776226 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 1.9997. Min Range: -1.9997

Max Act: 1.4647. Min Act: -0.0000

Data Index: 670571 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 1.9997. Min Range: -1.9997

Max Act: 1.3074. Min Act: -0.0000

Data Index: 1416907 (Python Code)

Max Activating Token Index: 736

Text #18

Max Range: 1.9997. Min Range: -1.9997

Max Act: 1.4600. Min Act: -0.0000

Data Index: 927653 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 1.9997. Min Range: -1.9997

Max Act: 1.4147. Min Act: -0.0000

Data Index: 663012 (C4 (Web Text))

Max Activating Token Index: 263