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

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

Neuron 2972 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3892. Min Range: -1.3892

Max Act: 1.3892. Min Act: -0.0000

Data Index: 22352 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 1.3892. Min Range: -1.3892

Max Act: 0.9927. Min Act: -0.0000

Data Index: 698927 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 1.3892. Min Range: -1.3892

Max Act: 0.9697. Min Act: -0.0001

Data Index: 1174248 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 1.3892. Min Range: -1.3892

Max Act: 0.9435. Min Act: -0.0000

Data Index: 184396 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 1.3892. Min Range: -1.3892

Max Act: 0.7946. Min Act: -0.0000

Data Index: 231350 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 1.3892. Min Range: -1.3892

Max Act: 0.7610. Min Act: -0.0001

Data Index: 1319417 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 1.3892. Min Range: -1.3892

Max Act: 0.7490. Min Act: -0.0001

Data Index: 628078 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 1.3892. Min Range: -1.3892

Max Act: 0.7141. Min Act: -0.0000

Data Index: 957732 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 1.3892. Min Range: -1.3892

Max Act: 0.7631. Min Act: -0.0001

Data Index: 1189387 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 1.3892. Min Range: -1.3892

Max Act: 0.7504. Min Act: -0.0001

Data Index: 110321 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 1.3892. Min Range: -1.3892

Max Act: 0.6968. Min Act: -0.0001

Data Index: 316260 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 1.3892. Min Range: -1.3892

Max Act: 0.6907. Min Act: -0.0001

Data Index: 564101 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 1.3892. Min Range: -1.3892

Max Act: 0.7048. Min Act: -0.0001

Data Index: 128473 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 1.3892. Min Range: -1.3892

Max Act: 0.7027. Min Act: -0.0001

Data Index: 1167324 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 1.3892. Min Range: -1.3892

Max Act: 0.6076. Min Act: -0.0001

Data Index: 1125588 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 1.3892. Min Range: -1.3892

Max Act: 0.6746. Min Act: -0.0001

Data Index: 168794 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 1.3892. Min Range: -1.3892

Max Act: 0.7095. Min Act: -0.0001

Data Index: 396610 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 1.3892. Min Range: -1.3892

Max Act: 0.6823. Min Act: -0.0001

Data Index: 984200 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 1.3892. Min Range: -1.3892

Max Act: 0.6521. Min Act: -0.0000

Data Index: 395533 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 1.3892. Min Range: -1.3892

Max Act: 0.6732. Min Act: -0.0000

Data Index: 1101043 (C4 (Web Text))

Max Activating Token Index: 824