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

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

Neuron 1072 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: 0.4438. Min Range: -0.4438

Max Act: 0.4438. Min Act: -0.0001

Data Index: 155320 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.4152. Min Act: -0.0001

Data Index: 1239 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.3650. Min Act: -0.0000

Data Index: 845423 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.3659. Min Act: -0.0001

Data Index: 202131 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.3574. Min Act: -0.0000

Data Index: 1357196 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.3635. Min Act: -0.0000

Data Index: 486206 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.3341. Min Act: -0.0001

Data Index: 1137949 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.3213. Min Act: -0.0000

Data Index: 411609 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.3107. Min Act: -0.0000

Data Index: 996972 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2807. Min Act: -0.0000

Data Index: 379067 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2877. Min Act: -0.0001

Data Index: 650918 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2734. Min Act: -0.0001

Data Index: 872838 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2723. Min Act: -0.0001

Data Index: 1198803 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2418. Min Act: -0.0001

Data Index: 773210 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2595. Min Act: -0.0001

Data Index: 846319 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2711. Min Act: -0.0001

Data Index: 1054152 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2765. Min Act: -0.0000

Data Index: 964565 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2699. Min Act: -0.0001

Data Index: 1276590 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2528. Min Act: -0.0001

Data Index: 787388 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 0.4438. Min Range: -0.4438

Max Act: 0.2593. Min Act: -0.0001

Data Index: 379057 (C4 (Web Text))

Max Activating Token Index: 654