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

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

Neuron 766 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.5569. Min Act: -0.0001

Data Index: 1216544 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.5189. Min Act: -0.0001

Data Index: 229615 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.4524. Min Act: -0.0000

Data Index: 181859 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.4471. Min Act: -0.0000

Data Index: 910788 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.4522. Min Act: -0.0000

Data Index: 804992 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.4519. Min Act: -0.0000

Data Index: 342655 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.4365. Min Act: 0.0000

Data Index: 289638 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.4513. Min Act: -0.0000

Data Index: 741539 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.4274. Min Act: -0.0000

Data Index: 1118900 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.4074. Min Act: -0.0000

Data Index: 354753 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.4240. Min Act: -0.0000

Data Index: 166402 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.4060. Min Act: -0.0001

Data Index: 420668 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.4017. Min Act: -0.0000

Data Index: 530617 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.3948. Min Act: 0.0000

Data Index: 724881 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.3981. Min Act: -0.0001

Data Index: 521897 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.3904. Min Act: -0.0000

Data Index: 1149936 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.3876. Min Act: -0.0000

Data Index: 229785 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.3871. Min Act: -0.0001

Data Index: 798764 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.3992. Min Act: 0.0000

Data Index: 1000709 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.3855. Min Act: -0.0000

Data Index: 110895 (C4 (Web Text))

Max Activating Token Index: 562