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

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

Neuron 3958 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1106. Min Range: -1.1106

Max Act: 1.1106. Min Act: -0.0000

Data Index: 1209859 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 1.1106. Min Range: -1.1106

Max Act: 1.0764. Min Act: -0.0000

Data Index: 249590 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.9436. Min Act: -0.0000

Data Index: 236874 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 1.1106. Min Range: -1.1106

Max Act: 1.0083. Min Act: -0.0000

Data Index: 390799 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 1.1106. Min Range: -1.1106

Max Act: 1.0690. Min Act: -0.0000

Data Index: 240687 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.9958. Min Act: -0.0000

Data Index: 560108 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.9328. Min Act: -0.0000

Data Index: 492835 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.8658. Min Act: -0.0000

Data Index: 738108 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.8903. Min Act: -0.0000

Data Index: 817578 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.9187. Min Act: -0.0000

Data Index: 224577 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.8684. Min Act: -0.0000

Data Index: 1159844 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.8628. Min Act: -0.0000

Data Index: 884044 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.8377. Min Act: -0.0000

Data Index: 890722 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.8191. Min Act: -0.0000

Data Index: 1188344 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.8921. Min Act: -0.0000

Data Index: 802805 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.8847. Min Act: -0.0000

Data Index: 293720 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.8091. Min Act: -0.0000

Data Index: 1240640 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.8523. Min Act: -0.0000

Data Index: 1103083 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.7728. Min Act: -0.0000

Data Index: 872387 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 1.1106. Min Range: -1.1106

Max Act: 0.7943. Min Act: -0.0000

Data Index: 306098 (C4 (Web Text))

Max Activating Token Index: 343