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

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

Neuron 2360 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.4345. Min Act: -0.0000

Data Index: 871149 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.2915. Min Act: -0.0000

Data Index: 237324 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.2042. Min Act: -0.0000

Data Index: 260085 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.1725. Min Act: -0.0000

Data Index: 266749 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.1367. Min Act: -0.0000

Data Index: 618856 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.1443. Min Act: -0.0000

Data Index: 387641 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.0624. Min Act: -0.0000

Data Index: 353562 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 1.4345. Min Range: -1.4345

Max Act: 0.9976. Min Act: -0.0000

Data Index: 1125532 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 1.4345. Min Range: -1.4345

Max Act: 0.8870. Min Act: -0.0000

Data Index: 1340935 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 1.4345. Min Range: -1.4345

Max Act: 0.9741. Min Act: -0.0000

Data Index: 151890 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 1.4345. Min Range: -1.4345

Max Act: 0.9243. Min Act: -0.0000

Data Index: 270331 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 1.4345. Min Range: -1.4345

Max Act: 0.9525. Min Act: -0.0000

Data Index: 835341 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 1.4345. Min Range: -1.4345

Max Act: 0.9359. Min Act: -0.0000

Data Index: 817942 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 1.4345. Min Range: -1.4345

Max Act: 0.8459. Min Act: -0.0000

Data Index: 766293 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 1.4345. Min Range: -1.4345

Max Act: 0.8335. Min Act: -0.0000

Data Index: 473073 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 1.4345. Min Range: -1.4345

Max Act: 0.9046. Min Act: -0.0000

Data Index: 132196 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 1.4345. Min Range: -1.4345

Max Act: 0.8336. Min Act: -0.0000

Data Index: 1043306 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 1.4345. Min Range: -1.4345

Max Act: 0.7895. Min Act: -0.0000

Data Index: 475988 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 1.4345. Min Range: -1.4345

Max Act: 0.8675. Min Act: -0.0000

Data Index: 443488 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 1.4345. Min Range: -1.4345

Max Act: 0.8098. Min Act: -0.0000

Data Index: 668014 (C4 (Web Text))

Max Activating Token Index: 48