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

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

Neuron 5386 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0415. Min Range: -1.0415

Max Act: 1.0415. Min Act: -0.0000

Data Index: 146696 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.8750. Min Act: -0.0000

Data Index: 781672 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.8434. Min Act: -0.0000

Data Index: 472451 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.7990. Min Act: -0.0000

Data Index: 902028 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.8422. Min Act: -0.0000

Data Index: 1020703 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.7989. Min Act: -0.0000

Data Index: 594670 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.7891. Min Act: -0.0000

Data Index: 913885 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.7948. Min Act: 0.0000

Data Index: 1337242 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.7684. Min Act: -0.0000

Data Index: 193358 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.8231. Min Act: -0.0000

Data Index: 981332 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.7685. Min Act: -0.0000

Data Index: 492070 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.7239. Min Act: -0.0000

Data Index: 724008 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.7148. Min Act: 0.0000

Data Index: 989859 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.7399. Min Act: -0.0000

Data Index: 65962 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.6972. Min Act: -0.0000

Data Index: 493876 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.6886. Min Act: 0.0000

Data Index: 20160 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.6409. Min Act: -0.0000

Data Index: 93216 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.6824. Min Act: -0.0000

Data Index: 192235 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.6981. Min Act: -0.0000

Data Index: 57268 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.6961. Min Act: -0.0000

Data Index: 232838 (C4 (Web Text))

Max Activating Token Index: 973