Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2997 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.9233. Min Act: -0.0002

Data Index: 75550 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.9015. Min Act: -0.0002

Data Index: 440484 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.8574. Min Act: -0.0002

Data Index: 562692 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.8643. Min Act: -0.0002

Data Index: 1084225 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.8592. Min Act: -0.0002

Data Index: 653712 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.8534. Min Act: -0.0002

Data Index: 837355 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.7197. Min Act: -0.0002

Data Index: 756976 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.8686. Min Act: -0.0002

Data Index: 605717 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.7882. Min Act: -0.0002

Data Index: 69820 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.8359. Min Act: -0.0002

Data Index: 114516 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.7372. Min Act: -0.0002

Data Index: 1159559 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.6961. Min Act: -0.0002

Data Index: 259904 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.8339. Min Act: -0.0002

Data Index: 820927 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.8383. Min Act: -0.0002

Data Index: 1311936 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.7319. Min Act: -0.0002

Data Index: 653616 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.6566. Min Act: -0.0002

Data Index: 1067420 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.7271. Min Act: -0.0002

Data Index: 319454 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.7168. Min Act: -0.0002

Data Index: 110472 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.7593. Min Act: -0.0002

Data Index: 12828 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 0.9233. Min Range: -0.9233

Max Act: 0.7565. Min Act: -0.0002

Data Index: 692967 (C4 (Web Text))

Max Activating Token Index: 17