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

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

Neuron 5279 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.8109. Min Act: -0.0000

Data Index: 251677 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.6942. Min Act: -0.0000

Data Index: 1096296 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.8405. Min Act: -0.0000

Data Index: 677495 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.6399. Min Act: -0.0000

Data Index: 412520 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.7196. Min Act: -0.0000

Data Index: 1356037 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.6152. Min Act: -0.0000

Data Index: 762749 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.6852. Min Act: -0.0000

Data Index: 694399 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.6748. Min Act: -0.0000

Data Index: 1044183 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.4857. Min Act: -0.0000

Data Index: 947107 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.6708. Min Act: -0.0000

Data Index: 1413865 (Python Code)

Max Activating Token Index: 279

Text #10

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.6523. Min Act: -0.0000

Data Index: 48849 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.6379. Min Act: -0.0000

Data Index: 270618 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.7961. Min Act: -0.0000

Data Index: 1417975 (Python Code)

Max Activating Token Index: 849

Text #13

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.6154. Min Act: -0.0000

Data Index: 1549335 (Python Code)

Max Activating Token Index: 128

Text #14

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.5945. Min Act: -0.0000

Data Index: 543837 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.5101. Min Act: -0.0000

Data Index: 1626456 (Python Code)

Max Activating Token Index: 45

Text #16

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.5793. Min Act: -0.0000

Data Index: 803348 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.5748. Min Act: -0.0000

Data Index: 873901 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.4708. Min Act: -0.0000

Data Index: 855836 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 1.8405. Min Range: -1.8405

Max Act: 1.4824. Min Act: -0.0000

Data Index: 1575328 (Python Code)

Max Activating Token Index: 694