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

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

Neuron 3958 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.7591. Min Act: -0.0000

Data Index: 153479 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.7393. Min Act: -0.0001

Data Index: 929827 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.7508. Min Act: -0.0001

Data Index: 962883 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.6375. Min Act: -0.0000

Data Index: 1111907 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.5890. Min Act: -0.0000

Data Index: 1304139 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.5154. Min Act: -0.0001

Data Index: 410593 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.5086. Min Act: -0.0001

Data Index: 1349261 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.5362. Min Act: -0.0001

Data Index: 172480 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.5517. Min Act: -0.0001

Data Index: 313220 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.4378. Min Act: -0.0000

Data Index: 895573 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.4290. Min Act: -0.0001

Data Index: 1074391 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.4537. Min Act: -0.0001

Data Index: 1251156 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.4074. Min Act: -0.0000

Data Index: 1024699 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.4129. Min Act: -0.0000

Data Index: 911570 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.4076. Min Act: -0.0001

Data Index: 829743 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.4367. Min Act: -0.0001

Data Index: 395717 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.3252. Min Act: -0.0000

Data Index: 409310 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.3830. Min Act: -0.0000

Data Index: 582064 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.3800. Min Act: -0.0001

Data Index: 77160 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 1.7591. Min Range: -1.7591

Max Act: 1.3561. Min Act: -0.0000

Data Index: 139654 (C4 (Web Text))

Max Activating Token Index: 461