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

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

Neuron 2538 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5050. Min Range: -4.5050

Max Act: 4.5050. Min Act: -0.0000

Data Index: 86405 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 4.5050. Min Range: -4.5050

Max Act: 3.0955. Min Act: -0.0000

Data Index: 863053 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 4.5050. Min Range: -4.5050

Max Act: 2.7049. Min Act: -0.0000

Data Index: 1035492 (C4 (Web Text))

Max Activating Token Index: 960

Text #3

Max Range: 4.5050. Min Range: -4.5050

Max Act: 2.5116. Min Act: -0.0000

Data Index: 54244 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 4.5050. Min Range: -4.5050

Max Act: 2.4822. Min Act: -0.0000

Data Index: 877319 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 4.5050. Min Range: -4.5050

Max Act: 2.3250. Min Act: -0.0000

Data Index: 1065377 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 4.5050. Min Range: -4.5050

Max Act: 2.4110. Min Act: -0.0000

Data Index: 1057208 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 4.5050. Min Range: -4.5050

Max Act: 2.2554. Min Act: -0.0000

Data Index: 271044 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 4.5050. Min Range: -4.5050

Max Act: 2.3500. Min Act: -0.0000

Data Index: 493789 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 4.5050. Min Range: -4.5050

Max Act: 2.3414. Min Act: -0.0000

Data Index: 1030292 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 4.5050. Min Range: -4.5050

Max Act: 2.4602. Min Act: -0.0000

Data Index: 65697 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 4.5050. Min Range: -4.5050

Max Act: 2.3304. Min Act: -0.0000

Data Index: 429731 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 4.5050. Min Range: -4.5050

Max Act: 2.1756. Min Act: -0.0000

Data Index: 653271 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 4.5050. Min Range: -4.5050

Max Act: 2.2686. Min Act: -0.0000

Data Index: 597062 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 4.5050. Min Range: -4.5050

Max Act: 2.3091. Min Act: -0.0000

Data Index: 58962 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 4.5050. Min Range: -4.5050

Max Act: 2.1763. Min Act: -0.0000

Data Index: 849480 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 4.5050. Min Range: -4.5050

Max Act: 2.0670. Min Act: -0.0000

Data Index: 745326 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 4.5050. Min Range: -4.5050

Max Act: 2.1563. Min Act: 0.0000

Data Index: 775201 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 4.5050. Min Range: -4.5050

Max Act: 2.0204. Min Act: 0.0000

Data Index: 102804 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 4.5050. Min Range: -4.5050

Max Act: 2.0882. Min Act: -0.0000

Data Index: 796937 (C4 (Web Text))

Max Activating Token Index: 26