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

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

Neuron 304 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.4658. Min Act: -0.0001

Data Index: 1317721 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.4551. Min Act: -0.0001

Data Index: 250677 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.4014. Min Act: -0.0001

Data Index: 293063 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.3971. Min Act: -0.0001

Data Index: 981960 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.3058. Min Act: -0.0001

Data Index: 926873 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.2211. Min Act: -0.0001

Data Index: 422119 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.2746. Min Act: -0.0001

Data Index: 301933 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.2309. Min Act: -0.0001

Data Index: 971303 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.2184. Min Act: -0.0001

Data Index: 775767 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.2273. Min Act: -0.0001

Data Index: 497170 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.2381. Min Act: -0.0000

Data Index: 255465 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0452. Min Act: -0.0001

Data Index: 929402 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0843. Min Act: -0.0000

Data Index: 1202523 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.2342. Min Act: -0.0001

Data Index: 934656 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.1490. Min Act: -0.0001

Data Index: 417205 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.1396. Min Act: -0.0000

Data Index: 427997 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0351. Min Act: -0.0001

Data Index: 989233 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 1.4658. Min Range: -1.4658

Max Act: 1.0661. Min Act: -0.0000

Data Index: 373949 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 1.4658. Min Range: -1.4658

Max Act: 0.9976. Min Act: -0.0000

Data Index: 1130273 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 1.4658. Min Range: -1.4658

Max Act: 0.9311. Min Act: -0.0000

Data Index: 581442 (C4 (Web Text))

Max Activating Token Index: 117