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

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

Neuron 5502 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: 0.5633. Min Range: -0.5633

Max Act: 0.5633. Min Act: -0.0000

Data Index: 853604 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.5448. Min Act: -0.0000

Data Index: 592520 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1096419 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.4593. Min Act: -0.0000

Data Index: 371102 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.4759. Min Act: -0.0000

Data Index: 154698 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.4261. Min Act: -0.0000

Data Index: 167337 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.3680. Min Act: -0.0000

Data Index: 87623 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.3305. Min Act: 0.0000

Data Index: 899003 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.3093. Min Act: -0.0000

Data Index: 1324213 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.3101. Min Act: -0.0000

Data Index: 531508 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.3185. Min Act: -0.0000

Data Index: 434049 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1205794 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.3064. Min Act: -0.0000

Data Index: 675253 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.3268. Min Act: -0.0000

Data Index: 949861 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.2959. Min Act: -0.0000

Data Index: 1275988 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.3008. Min Act: -0.0000

Data Index: 1191810 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.2987. Min Act: -0.0000

Data Index: 740951 (C4 (Web Text))

Max Activating Token Index: 614

Text #17

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1180040 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.2934. Min Act: -0.0000

Data Index: 1220445 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.2968. Min Act: -0.0000

Data Index: 97149 (C4 (Web Text))

Max Activating Token Index: 582