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

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

Neuron 2502 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.8259. Min Act: -0.0001

Data Index: 330138 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.8346. Min Act: -0.0001

Data Index: 634243 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.8686. Min Act: -0.0001

Data Index: 440484 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.9434. Min Act: -0.0001

Data Index: 477993 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.8591. Min Act: -0.0001

Data Index: 551151 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7494. Min Act: -0.0001

Data Index: 1173816 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7632. Min Act: -0.0001

Data Index: 1149715 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7733. Min Act: -0.0001

Data Index: 998685 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.6939. Min Act: -0.0001

Data Index: 31248 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7133. Min Act: -0.0001

Data Index: 1004284 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7538. Min Act: -0.0001

Data Index: 944639 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.6654. Min Act: -0.0001

Data Index: 576377 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.6722. Min Act: -0.0001

Data Index: 1176868 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.6758. Min Act: -0.0001

Data Index: 839123 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7028. Min Act: -0.0001

Data Index: 693185 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.6808. Min Act: -0.0001

Data Index: 527157 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.6984. Min Act: -0.0001

Data Index: 615058 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.6360. Min Act: -0.0001

Data Index: 1188975 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.6871. Min Act: -0.0001

Data Index: 1052257 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.6504. Min Act: -0.0001

Data Index: 18540 (C4 (Web Text))

Max Activating Token Index: 87