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

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

Neuron 696 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.7288. Min Act: -0.0001

Data Index: 610180 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6791. Min Act: -0.0001

Data Index: 844374 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.7293. Min Act: -0.0001

Data Index: 759317 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6934. Min Act: -0.0001

Data Index: 1066077 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6561. Min Act: -0.0001

Data Index: 942688 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.7289. Min Act: -0.0001

Data Index: 840773 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6809. Min Act: -0.0001

Data Index: 1070308 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.7175. Min Act: -0.0001

Data Index: 903381 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6580. Min Act: -0.0001

Data Index: 829249 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6497. Min Act: -0.0001

Data Index: 379690 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6514. Min Act: -0.0001

Data Index: 263483 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6270. Min Act: -0.0001

Data Index: 917242 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6458. Min Act: -0.0001

Data Index: 1088724 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6512. Min Act: -0.0001

Data Index: 454427 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6263. Min Act: -0.0001

Data Index: 941910 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6443. Min Act: -0.0001

Data Index: 948528 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6694. Min Act: -0.0001

Data Index: 362045 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6811. Min Act: -0.0001

Data Index: 259924 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6790. Min Act: -0.0001

Data Index: 697505 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.7293. Min Range: -0.7293

Max Act: 0.6415. Min Act: -0.0001

Data Index: 884872 (C4 (Web Text))

Max Activating Token Index: 162