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

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

Neuron 3529 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4646. Min Range: -2.4646

Max Act: 2.4646. Min Act: -0.0000

Data Index: 300731 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 2.4646. Min Range: -2.4646

Max Act: 2.3547. Min Act: -0.0000

Data Index: 149257 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 2.4646. Min Range: -2.4646

Max Act: 2.2093. Min Act: -0.0000

Data Index: 318913 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 2.4646. Min Range: -2.4646

Max Act: 1.8817. Min Act: -0.0000

Data Index: 185621 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 2.4646. Min Range: -2.4646

Max Act: 1.8404. Min Act: -0.0000

Data Index: 649655 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 2.4646. Min Range: -2.4646

Max Act: 1.7165. Min Act: -0.0000

Data Index: 230791 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 2.4646. Min Range: -2.4646

Max Act: 1.7958. Min Act: -0.0000

Data Index: 987129 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 2.4646. Min Range: -2.4646

Max Act: 1.6616. Min Act: -0.0000

Data Index: 1280230 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 2.4646. Min Range: -2.4646

Max Act: 1.6475. Min Act: -0.0000

Data Index: 1310797 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 2.4646. Min Range: -2.4646

Max Act: 1.8446. Min Act: -0.0000

Data Index: 352700 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 2.4646. Min Range: -2.4646

Max Act: 1.6480. Min Act: -0.0000

Data Index: 634785 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 2.4646. Min Range: -2.4646

Max Act: 1.7342. Min Act: -0.0000

Data Index: 791656 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 2.4646. Min Range: -2.4646

Max Act: 1.7105. Min Act: -0.0000

Data Index: 1233252 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 2.4646. Min Range: -2.4646

Max Act: 1.7585. Min Act: -0.0000

Data Index: 412926 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 2.4646. Min Range: -2.4646

Max Act: 1.6653. Min Act: -0.0000

Data Index: 1332719 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 2.4646. Min Range: -2.4646

Max Act: 1.7168. Min Act: -0.0000

Data Index: 143781 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 2.4646. Min Range: -2.4646

Max Act: 1.6297. Min Act: -0.0000

Data Index: 1142550 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 2.4646. Min Range: -2.4646

Max Act: 1.5465. Min Act: -0.0000

Data Index: 1059679 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 2.4646. Min Range: -2.4646

Max Act: 1.5933. Min Act: -0.0000

Data Index: 201605 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 2.4646. Min Range: -2.4646

Max Act: 1.5683. Min Act: -0.0000

Data Index: 242397 (C4 (Web Text))

Max Activating Token Index: 575