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

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

Neuron 2400 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5985. Min Act: -0.0001

Data Index: 402714 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5448. Min Act: -0.0001

Data Index: 133239 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5183. Min Act: -0.0001

Data Index: 544824 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5095. Min Act: -0.0001

Data Index: 579827 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5178. Min Act: -0.0001

Data Index: 1237744 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5070. Min Act: -0.0001

Data Index: 1026190 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4616. Min Act: -0.0001

Data Index: 559642 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4863. Min Act: -0.0001

Data Index: 1182690 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5155. Min Act: -0.0001

Data Index: 1167251 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4793. Min Act: -0.0001

Data Index: 1165222 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4763. Min Act: -0.0001

Data Index: 355108 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4913. Min Act: -0.0001

Data Index: 435820 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4613. Min Act: -0.0001

Data Index: 837801 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4455. Min Act: -0.0001

Data Index: 312044 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4721. Min Act: -0.0001

Data Index: 1167666 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4880. Min Act: -0.0001

Data Index: 807059 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4706. Min Act: -0.0001

Data Index: 867619 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4557. Min Act: -0.0001

Data Index: 1040610 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4666. Min Act: -0.0001

Data Index: 924724 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4578. Min Act: -0.0001

Data Index: 1313219 (C4 (Web Text))

Max Activating Token Index: 822