Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4883 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 9.4521. Min Range: -9.4521

Max Act: 8.8575. Min Act: -0.0000

Data Index: 717359 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 9.4521. Min Range: -9.4521

Max Act: 9.4521. Min Act: -0.0000

Data Index: 546131 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 9.4521. Min Range: -9.4521

Max Act: 8.8140. Min Act: -0.0000

Data Index: 940876 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 9.4521. Min Range: -9.4521

Max Act: 8.6091. Min Act: -0.0000

Data Index: 782465 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 9.4521. Min Range: -9.4521

Max Act: 9.0591. Min Act: -0.0000

Data Index: 1185530 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 9.4521. Min Range: -9.4521

Max Act: 8.6135. Min Act: -0.0000

Data Index: 1000283 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 9.4521. Min Range: -9.4521

Max Act: 8.4465. Min Act: -0.0000

Data Index: 1348787 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 9.4521. Min Range: -9.4521

Max Act: 8.1890. Min Act: -0.0000

Data Index: 192861 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 9.4521. Min Range: -9.4521

Max Act: 7.9986. Min Act: -0.0000

Data Index: 959071 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 9.4521. Min Range: -9.4521

Max Act: 7.7669. Min Act: -0.0000

Data Index: 202363 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 9.4521. Min Range: -9.4521

Max Act: 7.4170. Min Act: -0.0000

Data Index: 1060340 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 9.4521. Min Range: -9.4521

Max Act: 7.2726. Min Act: -0.0000

Data Index: 1127114 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 9.4521. Min Range: -9.4521

Max Act: 8.0842. Min Act: -0.0000

Data Index: 1286656 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 9.4521. Min Range: -9.4521

Max Act: 6.5984. Min Act: -0.0000

Data Index: 926358 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 9.4521. Min Range: -9.4521

Max Act: 7.5719. Min Act: -0.0000

Data Index: 992580 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 9.4521. Min Range: -9.4521

Max Act: 7.0748. Min Act: -0.0000

Data Index: 544948 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 9.4521. Min Range: -9.4521

Max Act: 6.9998. Min Act: -0.0000

Data Index: 960068 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 9.4521. Min Range: -9.4521

Max Act: 6.9684. Min Act: -0.0000

Data Index: 1096470 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 9.4521. Min Range: -9.4521

Max Act: 7.9159. Min Act: -0.0000

Data Index: 874441 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 9.4521. Min Range: -9.4521

Max Act: 7.2868. Min Act: -0.0000

Data Index: 570871 (C4 (Web Text))

Max Activating Token Index: 26