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

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

Neuron 5227 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: 1.1951. Min Range: -1.1951

Max Act: 1.1951. Min Act: -0.0000

Data Index: 313860 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 1.1951. Min Range: -1.1951

Max Act: 1.1689. Min Act: -0.0000

Data Index: 60672 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 1.1951. Min Range: -1.1951

Max Act: 1.0987. Min Act: -0.0000

Data Index: 128414 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 1.1951. Min Range: -1.1951

Max Act: 1.0981. Min Act: -0.0000

Data Index: 120106 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 1.1951. Min Range: -1.1951

Max Act: 1.0098. Min Act: -0.0000

Data Index: 701684 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 1.1951. Min Range: -1.1951

Max Act: 0.9740. Min Act: -0.0000

Data Index: 20830 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 1.1951. Min Range: -1.1951

Max Act: 1.0966. Min Act: -0.0000

Data Index: 705782 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 1.1951. Min Range: -1.1951

Max Act: 0.9512. Min Act: -0.0000

Data Index: 1068213 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 1.1951. Min Range: -1.1951

Max Act: 1.0462. Min Act: -0.0000

Data Index: 1212665 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 1.1951. Min Range: -1.1951

Max Act: 0.9660. Min Act: -0.0000

Data Index: 1289230 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 1.1951. Min Range: -1.1951

Max Act: 0.8209. Min Act: -0.0000

Data Index: 173882 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 1.1951. Min Range: -1.1951

Max Act: 0.9079. Min Act: -0.0000

Data Index: 1395996 (Python Code)

Max Activating Token Index: 96

Text #12

Max Range: 1.1951. Min Range: -1.1951

Max Act: 0.9032. Min Act: -0.0000

Data Index: 619282 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 1.1951. Min Range: -1.1951

Max Act: 0.9018. Min Act: -0.0000

Data Index: 1228097 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 1.1951. Min Range: -1.1951

Max Act: 0.8479. Min Act: -0.0000

Data Index: 646902 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 1.1951. Min Range: -1.1951

Max Act: 0.8406. Min Act: -0.0000

Data Index: 949192 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 1.1951. Min Range: -1.1951

Max Act: 0.7953. Min Act: -0.0000

Data Index: 305802 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 1.1951. Min Range: -1.1951

Max Act: 0.7794. Min Act: -0.0000

Data Index: 1158110 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 1.1951. Min Range: -1.1951

Max Act: 0.8292. Min Act: -0.0000

Data Index: 118667 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 1.1951. Min Range: -1.1951

Max Act: 0.8011. Min Act: -0.0000

Data Index: 452068 (C4 (Web Text))

Max Activating Token Index: 401