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

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

Neuron 3781 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: 1.8883. Min Range: -1.8883

Max Act: 1.8883. Min Act: -0.0000

Data Index: 592795 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.8859. Min Act: -0.0000

Data Index: 888744 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.7819. Min Act: -0.0000

Data Index: 56132 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.7382. Min Act: -0.0000

Data Index: 668364 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.6310. Min Act: -0.0000

Data Index: 1039164 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.6963. Min Act: -0.0000

Data Index: 451171 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.5630. Min Act: -0.0000

Data Index: 23284 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.6649. Min Act: -0.0000

Data Index: 1358950 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.6362. Min Act: -0.0000

Data Index: 83464 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.6268. Min Act: -0.0000

Data Index: 88191 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.7103. Min Act: -0.0000

Data Index: 664434 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.5385. Min Act: -0.0000

Data Index: 437791 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.5817. Min Act: -0.0000

Data Index: 961748 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.4393. Min Act: -0.0000

Data Index: 893632 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.5822. Min Act: -0.0000

Data Index: 875111 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.4743. Min Act: -0.0000

Data Index: 459363 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.5160. Min Act: -0.0000

Data Index: 675993 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.6276. Min Act: -0.0000

Data Index: 39607 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.4050. Min Act: -0.0000

Data Index: 411511 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 1.8883. Min Range: -1.8883

Max Act: 1.5278. Min Act: -0.0000

Data Index: 556109 (C4 (Web Text))

Max Activating Token Index: 371