Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2459 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.5928. Min Act: -0.0001

Data Index: 9381 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4858. Min Act: -0.0001

Data Index: 13194 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.5159. Min Act: -0.0000

Data Index: 1346652 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4853. Min Act: -0.0001

Data Index: 761133 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.5029. Min Act: -0.0001

Data Index: 726930 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4506. Min Act: -0.0001

Data Index: 1186128 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4664. Min Act: -0.0001

Data Index: 1283108 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4514. Min Act: -0.0001

Data Index: 894637 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4442. Min Act: -0.0001

Data Index: 71017 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4709. Min Act: -0.0001

Data Index: 387059 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4751. Min Act: -0.0000

Data Index: 447685 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4427. Min Act: -0.0001

Data Index: 344350 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4406. Min Act: -0.0001

Data Index: 612412 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4538. Min Act: -0.0001

Data Index: 116204 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4543. Min Act: -0.0001

Data Index: 1042295 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4397. Min Act: -0.0001

Data Index: 62828 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4511. Min Act: -0.0000

Data Index: 606978 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4516. Min Act: -0.0001

Data Index: 319187 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4344. Min Act: -0.0001

Data Index: 511656 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.5928. Min Range: -0.5928

Max Act: 0.4321. Min Act: -0.0001

Data Index: 719448 (C4 (Web Text))

Max Activating Token Index: 221