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

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

Neuron 492 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.4391. Min Act: -0.0001

Data Index: 205999 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.4086. Min Act: -0.0001

Data Index: 39490 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.4202. Min Act: -0.0001

Data Index: 299512 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.4076. Min Act: -0.0001

Data Index: 298393 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3977. Min Act: -0.0001

Data Index: 1051894 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3398. Min Act: -0.0001

Data Index: 669144 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3680. Min Act: -0.0001

Data Index: 327339 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3552. Min Act: -0.0001

Data Index: 410055 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3474. Min Act: -0.0001

Data Index: 1170695 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3287. Min Act: -0.0001

Data Index: 1180920 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3461. Min Act: -0.0001

Data Index: 384622 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3590. Min Act: -0.0001

Data Index: 1084091 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3277. Min Act: -0.0001

Data Index: 797180 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3178. Min Act: -0.0001

Data Index: 153464 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3261. Min Act: -0.0001

Data Index: 942572 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.2875. Min Act: -0.0001

Data Index: 738806 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3118. Min Act: -0.0001

Data Index: 941005 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3314. Min Act: -0.0001

Data Index: 397300 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3224. Min Act: -0.0001

Data Index: 881716 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3199. Min Act: -0.0001

Data Index: 248016 (C4 (Web Text))

Max Activating Token Index: 43