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

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

Neuron 3567 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.7476. Min Act: -0.0000

Data Index: 1099967 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.6941. Min Act: -0.0000

Data Index: 1310428 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.4017. Min Act: -0.0000

Data Index: 468284 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.3369. Min Act: -0.0000

Data Index: 75839 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.3620. Min Act: -0.0000

Data Index: 357309 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.2824. Min Act: -0.0000

Data Index: 717242 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.3320. Min Act: -0.0000

Data Index: 379751 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.1866. Min Act: -0.0000

Data Index: 33269 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.2199. Min Act: -0.0000

Data Index: 369266 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.2461. Min Act: -0.0000

Data Index: 893114 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.2245. Min Act: -0.0000

Data Index: 57614 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.2668. Min Act: -0.0000

Data Index: 1284575 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.0192. Min Act: -0.0000

Data Index: 483185 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.3772. Min Act: -0.0000

Data Index: 176492 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.0853. Min Act: -0.0000

Data Index: 513211 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.1955. Min Act: -0.0001

Data Index: 1114793 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.0930. Min Act: -0.0000

Data Index: 336569 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.2387. Min Act: -0.0000

Data Index: 1118368 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.2365. Min Act: -0.0000

Data Index: 1314238 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 1.7476. Min Range: -1.7476

Max Act: 1.0133. Min Act: -0.0000

Data Index: 850334 (C4 (Web Text))

Max Activating Token Index: 759