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

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

Neuron 929 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: 0.4780. Min Range: -0.4780

Max Act: 0.4780. Min Act: -0.0001

Data Index: 1118288 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.4397. Min Act: -0.0001

Data Index: 545528 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3702. Min Act: -0.0000

Data Index: 25944 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.4406. Min Act: -0.0001

Data Index: 525816 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3968. Min Act: -0.0000

Data Index: 315473 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.4056. Min Act: -0.0000

Data Index: 720041 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3805. Min Act: -0.0001

Data Index: 623342 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3550. Min Act: -0.0001

Data Index: 136159 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3740. Min Act: -0.0000

Data Index: 393936 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3921. Min Act: -0.0001

Data Index: 1007565 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3507. Min Act: -0.0001

Data Index: 1013104 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3565. Min Act: -0.0000

Data Index: 1091524 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3823. Min Act: -0.0001

Data Index: 232707 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3642. Min Act: -0.0000

Data Index: 203803 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3848. Min Act: -0.0001

Data Index: 83908 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3368. Min Act: -0.0001

Data Index: 1074196 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3491. Min Act: -0.0000

Data Index: 1085245 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3513. Min Act: -0.0000

Data Index: 336455 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3716. Min Act: -0.0001

Data Index: 427986 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 0.4780. Min Range: -0.4780

Max Act: 0.3443. Min Act: -0.0001

Data Index: 146379 (C4 (Web Text))

Max Activating Token Index: 888