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

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

Neuron 4071 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: 0.6201. Min Range: -0.6201

Max Act: 0.6201. Min Act: -0.0002

Data Index: 889393 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5447. Min Act: -0.0002

Data Index: 528771 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.6159. Min Act: -0.0002

Data Index: 595733 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.6172. Min Act: -0.0002

Data Index: 564986 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.6095. Min Act: -0.0002

Data Index: 542811 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5820. Min Act: -0.0002

Data Index: 1163849 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5878. Min Act: -0.0002

Data Index: 388933 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5759. Min Act: -0.0002

Data Index: 1223945 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5934. Min Act: -0.0002

Data Index: 146998 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5937. Min Act: -0.0002

Data Index: 842071 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5526. Min Act: -0.0002

Data Index: 578728 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.6117. Min Act: -0.0002

Data Index: 791023 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5924. Min Act: -0.0002

Data Index: 274990 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5861. Min Act: -0.0002

Data Index: 722961 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5935. Min Act: -0.0002

Data Index: 193453 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5691. Min Act: -0.0002

Data Index: 1251200 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5891. Min Act: -0.0002

Data Index: 385452 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5825. Min Act: -0.0002

Data Index: 180540 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5644. Min Act: -0.0002

Data Index: 6149 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 0.6201. Min Range: -0.6201

Max Act: 0.5841. Min Act: -0.0002

Data Index: 1282028 (C4 (Web Text))

Max Activating Token Index: 520