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

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

Neuron 1851 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: 1.7820. Min Range: -1.7820

Max Act: 1.7820. Min Act: -0.0001

Data Index: 1310033 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.4911. Min Act: -0.0001

Data Index: 1187422 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.5032. Min Act: -0.0001

Data Index: 1347771 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.4202. Min Act: -0.0001

Data Index: 830763 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.3153. Min Act: -0.0001

Data Index: 1308868 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.3535. Min Act: -0.0001

Data Index: 1006878 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.3402. Min Act: -0.0001

Data Index: 434620 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.2360. Min Act: -0.0001

Data Index: 699888 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.2780. Min Act: -0.0001

Data Index: 1182022 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.2041. Min Act: -0.0001

Data Index: 152871 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.2312. Min Act: -0.0001

Data Index: 671062 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.2481. Min Act: -0.0001

Data Index: 619807 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.1701. Min Act: -0.0001

Data Index: 776240 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.1947. Min Act: -0.0001

Data Index: 220934 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.1633. Min Act: -0.0001

Data Index: 150927 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.1291. Min Act: -0.0001

Data Index: 543530 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.2213. Min Act: -0.0001

Data Index: 671295 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.1449. Min Act: -0.0001

Data Index: 881423 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.2830. Min Act: -0.0001

Data Index: 348594 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 1.7820. Min Range: -1.7820

Max Act: 1.2360. Min Act: -0.0001

Data Index: 1161296 (C4 (Web Text))

Max Activating Token Index: 37