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

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

Neuron 3820 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: 2.1504. Min Range: -2.1504

Max Act: 2.0174. Min Act: -0.0000

Data Index: 148190 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 2.1504. Min Range: -2.1504

Max Act: 2.1504. Min Act: -0.0000

Data Index: 761780 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.8170. Min Act: -0.0001

Data Index: 14501 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.8406. Min Act: -0.0001

Data Index: 21236 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.9155. Min Act: -0.0000

Data Index: 244376 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.7940. Min Act: -0.0000

Data Index: 385473 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.7784. Min Act: -0.0001

Data Index: 802044 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.7752. Min Act: -0.0001

Data Index: 494011 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.7793. Min Act: -0.0001

Data Index: 504625 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.7574. Min Act: -0.0000

Data Index: 896272 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.7561. Min Act: -0.0000

Data Index: 1311616 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.8452. Min Act: -0.0001

Data Index: 474125 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.6461. Min Act: -0.0000

Data Index: 320275 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.6329. Min Act: -0.0000

Data Index: 937800 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.7144. Min Act: -0.0000

Data Index: 337334 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.7043. Min Act: -0.0000

Data Index: 52597 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.6881. Min Act: -0.0000

Data Index: 805508 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.6657. Min Act: -0.0000

Data Index: 61565 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.6745. Min Act: -0.0001

Data Index: 586328 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 2.1504. Min Range: -2.1504

Max Act: 1.5604. Min Act: -0.0000

Data Index: 595773 (C4 (Web Text))

Max Activating Token Index: 940