Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3857 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4864. Min Range: -1.4864

Max Act: 1.4864. Min Act: -0.0000

Data Index: 871940 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 1.4864. Min Range: -1.4864

Max Act: 1.3514. Min Act: -0.0000

Data Index: 1328189 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 1.4864. Min Range: -1.4864

Max Act: 1.3529. Min Act: -0.0000

Data Index: 688253 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 1.4864. Min Range: -1.4864

Max Act: 1.3522. Min Act: -0.0000

Data Index: 461023 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 1.4864. Min Range: -1.4864

Max Act: 1.1469. Min Act: -0.0000

Data Index: 180754 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 1.4864. Min Range: -1.4864

Max Act: 0.9767. Min Act: -0.0000

Data Index: 1041509 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 1.4864. Min Range: -1.4864

Max Act: 0.9361. Min Act: -0.0000

Data Index: 1130375 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 1.4864. Min Range: -1.4864

Max Act: 0.9708. Min Act: -0.0000

Data Index: 1062506 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 1.4864. Min Range: -1.4864

Max Act: 0.8796. Min Act: -0.0000

Data Index: 603190 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 1.4864. Min Range: -1.4864

Max Act: 0.8975. Min Act: -0.0000

Data Index: 766953 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 1.4864. Min Range: -1.4864

Max Act: 0.8632. Min Act: -0.0000

Data Index: 365659 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 1.4864. Min Range: -1.4864

Max Act: 0.8699. Min Act: -0.0000

Data Index: 1038459 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 1.4864. Min Range: -1.4864

Max Act: 0.8330. Min Act: -0.0000

Data Index: 879018 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 1.4864. Min Range: -1.4864

Max Act: 0.8458. Min Act: -0.0000

Data Index: 224920 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 1.4864. Min Range: -1.4864

Max Act: 0.8723. Min Act: -0.0000

Data Index: 802729 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 1.4864. Min Range: -1.4864

Max Act: 0.8101. Min Act: -0.0000

Data Index: 625634 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 1.4864. Min Range: -1.4864

Max Act: 0.8049. Min Act: -0.0000

Data Index: 790937 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 1.4864. Min Range: -1.4864

Max Act: 0.8090. Min Act: -0.0000

Data Index: 270581 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 1.4864. Min Range: -1.4864

Max Act: 0.7743. Min Act: -0.0000

Data Index: 77219 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 1.4864. Min Range: -1.4864

Max Act: 0.8001. Min Act: -0.0000

Data Index: 1159203 (C4 (Web Text))

Max Activating Token Index: 788