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

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

Neuron 2714 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.2418. Min Range: -6.2418

Max Act: 6.2418. Min Act: -0.0001

Data Index: 617433 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 6.2418. Min Range: -6.2418

Max Act: 5.8702. Min Act: -0.0000

Data Index: 494195 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 6.2418. Min Range: -6.2418

Max Act: 6.0355. Min Act: -0.0001

Data Index: 1278236 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 6.2418. Min Range: -6.2418

Max Act: 5.9669. Min Act: -0.0001

Data Index: 462882 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 6.2418. Min Range: -6.2418

Max Act: 6.0352. Min Act: -0.0000

Data Index: 1045940 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 6.2418. Min Range: -6.2418

Max Act: 5.8441. Min Act: -0.0001

Data Index: 742375 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 6.2418. Min Range: -6.2418

Max Act: 5.8464. Min Act: -0.0000

Data Index: 541957 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 6.2418. Min Range: -6.2418

Max Act: 5.2842. Min Act: -0.0001

Data Index: 366744 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 6.2418. Min Range: -6.2418

Max Act: 5.3648. Min Act: -0.0000

Data Index: 883362 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 6.2418. Min Range: -6.2418

Max Act: 5.5362. Min Act: -0.0001

Data Index: 1184474 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 6.2418. Min Range: -6.2418

Max Act: 5.5524. Min Act: -0.0001

Data Index: 1079293 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 6.2418. Min Range: -6.2418

Max Act: 5.4788. Min Act: -0.0001

Data Index: 518236 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 6.2418. Min Range: -6.2418

Max Act: 5.6598. Min Act: -0.0001

Data Index: 1254416 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 6.2418. Min Range: -6.2418

Max Act: 4.8105. Min Act: -0.0001

Data Index: 150786 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 6.2418. Min Range: -6.2418

Max Act: 4.8188. Min Act: -0.0000

Data Index: 102542 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 6.2418. Min Range: -6.2418

Max Act: 4.7846. Min Act: -0.0001

Data Index: 659909 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 6.2418. Min Range: -6.2418

Max Act: 4.9165. Min Act: -0.0001

Data Index: 541396 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 6.2418. Min Range: -6.2418

Max Act: 5.0548. Min Act: -0.0001

Data Index: 873938 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 6.2418. Min Range: -6.2418

Max Act: 5.2366. Min Act: -0.0001

Data Index: 1077851 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 6.2418. Min Range: -6.2418

Max Act: 4.8835. Min Act: -0.0001

Data Index: 1305912 (C4 (Web Text))

Max Activating Token Index: 469