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

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

Neuron 4146 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.7800. Min Act: -0.0000

Data Index: 586031 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.7653. Min Act: -0.0000

Data Index: 475405 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.7970. Min Act: -0.0000

Data Index: 42942 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.7371. Min Act: -0.0000

Data Index: 334328 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.6931. Min Act: -0.0000

Data Index: 458746 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.6962. Min Act: -0.0000

Data Index: 629269 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.6680. Min Act: -0.0000

Data Index: 156446 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.6324. Min Act: -0.0000

Data Index: 883680 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.6512. Min Act: -0.0000

Data Index: 166639 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.5986. Min Act: -0.0000

Data Index: 350457 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.4557. Min Act: -0.0000

Data Index: 366597 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.4286. Min Act: -0.0000

Data Index: 1095682 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.4077. Min Act: -0.0000

Data Index: 698962 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.4186. Min Act: -0.0000

Data Index: 147242 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.3707. Min Act: -0.0000

Data Index: 1194459 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.3571. Min Act: -0.0000

Data Index: 578109 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.3947. Min Act: -0.0000

Data Index: 561492 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.3502. Min Act: -0.0000

Data Index: 516863 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.3369. Min Act: -0.0000

Data Index: 801030 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.7970. Min Range: -0.7970

Max Act: 0.3470. Min Act: -0.0000

Data Index: 295903 (C4 (Web Text))

Max Activating Token Index: 234