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

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

Neuron 1009 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9338. Min Range: -3.9338

Max Act: 3.9338. Min Act: -0.0000

Data Index: 348919 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 3.9338. Min Range: -3.9338

Max Act: 3.8869. Min Act: -0.0000

Data Index: 1003393 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 3.9338. Min Range: -3.9338

Max Act: 3.8237. Min Act: -0.0000

Data Index: 1292724 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 3.9338. Min Range: -3.9338

Max Act: 3.2505. Min Act: -0.0000

Data Index: 1178289 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 3.9338. Min Range: -3.9338

Max Act: 2.8012. Min Act: -0.0000

Data Index: 471925 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 3.9338. Min Range: -3.9338

Max Act: 2.5739. Min Act: -0.0000

Data Index: 142498 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 3.9338. Min Range: -3.9338

Max Act: 2.4225. Min Act: -0.0000

Data Index: 1293015 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 3.9338. Min Range: -3.9338

Max Act: 2.6169. Min Act: -0.0000

Data Index: 945995 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 3.9338. Min Range: -3.9338

Max Act: 2.4076. Min Act: -0.0000

Data Index: 469590 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 3.9338. Min Range: -3.9338

Max Act: 2.3794. Min Act: -0.0000

Data Index: 265017 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 3.9338. Min Range: -3.9338

Max Act: 2.3435. Min Act: -0.0000

Data Index: 133953 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 3.9338. Min Range: -3.9338

Max Act: 2.2678. Min Act: -0.0000

Data Index: 50250 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 3.9338. Min Range: -3.9338

Max Act: 2.2387. Min Act: -0.0000

Data Index: 867860 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 3.9338. Min Range: -3.9338

Max Act: 2.2387. Min Act: -0.0000

Data Index: 1458188 (Python Code)

Max Activating Token Index: 717

Text #14

Max Range: 3.9338. Min Range: -3.9338

Max Act: 2.1997. Min Act: -0.0000

Data Index: 657387 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 3.9338. Min Range: -3.9338

Max Act: 2.1718. Min Act: -0.0000

Data Index: 860392 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 3.9338. Min Range: -3.9338

Max Act: 2.1485. Min Act: -0.0000

Data Index: 1005807 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 3.9338. Min Range: -3.9338

Max Act: 2.0458. Min Act: -0.0000

Data Index: 132148 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 3.9338. Min Range: -3.9338

Max Act: 2.1312. Min Act: -0.0000

Data Index: 979477 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 3.9338. Min Range: -3.9338

Max Act: 2.0058. Min Act: -0.0000

Data Index: 1355335 (C4 (Web Text))

Max Activating Token Index: 851