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

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

Neuron 1506 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0624. Min Act: -0.0003

Data Index: 1173895 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0535. Min Act: -0.0001

Data Index: 1178231 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0498. Min Act: -0.0002

Data Index: 389179 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0498. Min Act: -0.0001

Data Index: 334307 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0480. Min Act: -0.0002

Data Index: 134687 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0476. Min Act: -0.0001

Data Index: 68779 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1077075 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0478. Min Act: -0.0001

Data Index: 360046 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0452. Min Act: -0.0002

Data Index: 546169 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0442. Min Act: -0.0003

Data Index: 1139797 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0439. Min Act: -0.0001

Data Index: 465158 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0432. Min Act: -0.0003

Data Index: 237827 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0431. Min Act: -0.0002

Data Index: 372764 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0422. Min Act: -0.0002

Data Index: 89143 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0417. Min Act: -0.0003

Data Index: 92639 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0411. Min Act: -0.0001

Data Index: 54698 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0427. Min Act: -0.0002

Data Index: 737739 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0407. Min Act: -0.0001

Data Index: 856463 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0407. Min Act: -0.0001

Data Index: 997613 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0402. Min Act: -0.0003

Data Index: 698180 (C4 (Web Text))

Max Activating Token Index: 119