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

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

Neuron 1379 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7819. Min Range: -1.7819

Max Act: 1.7819. Min Act: -0.0000

Data Index: 255245 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 1.7819. Min Range: -1.7819

Max Act: 1.4827. Min Act: -0.0000

Data Index: 412584 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 1.7819. Min Range: -1.7819

Max Act: 1.5367. Min Act: -0.0000

Data Index: 1094915 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 1.7819. Min Range: -1.7819

Max Act: 1.4812. Min Act: -0.0000

Data Index: 170922 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 1.7819. Min Range: -1.7819

Max Act: 1.6105. Min Act: -0.0000

Data Index: 733320 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 1.7819. Min Range: -1.7819

Max Act: 1.2528. Min Act: -0.0000

Data Index: 1373251 (Python Code)

Max Activating Token Index: 296

Text #6

Max Range: 1.7819. Min Range: -1.7819

Max Act: 1.3256. Min Act: -0.0000

Data Index: 1635570 (Python Code)

Max Activating Token Index: 60

Text #7

Max Range: 1.7819. Min Range: -1.7819

Max Act: 1.3885. Min Act: -0.0000

Data Index: 279868 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 1.7819. Min Range: -1.7819

Max Act: 1.3369. Min Act: -0.0000

Data Index: 1587884 (Python Code)

Max Activating Token Index: 258

Text #9

Max Range: 1.7819. Min Range: -1.7819

Max Act: 1.3241. Min Act: -0.0000

Data Index: 1177026 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 1.7819. Min Range: -1.7819

Max Act: 1.4073. Min Act: -0.0000

Data Index: 434993 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 1.7819. Min Range: -1.7819

Max Act: 1.3537. Min Act: -0.0000

Data Index: 397845 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 1.7819. Min Range: -1.7819

Max Act: 1.2311. Min Act: -0.0000

Data Index: 1633090 (Python Code)

Max Activating Token Index: 575

Text #13

Max Range: 1.7819. Min Range: -1.7819

Max Act: 1.3043. Min Act: -0.0000

Data Index: 957179 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 1.7819. Min Range: -1.7819

Max Act: 1.2815. Min Act: -0.0000

Data Index: 976249 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 1.7819. Min Range: -1.7819

Max Act: 1.2820. Min Act: -0.0000

Data Index: 624320 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 1.7819. Min Range: -1.7819

Max Act: 1.2541. Min Act: -0.0000

Data Index: 65873 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 1.7819. Min Range: -1.7819

Max Act: 1.1892. Min Act: -0.0000

Data Index: 123969 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 1.7819. Min Range: -1.7819

Max Act: 1.3418. Min Act: -0.0000

Data Index: 1432084 (Python Code)

Max Activating Token Index: 788

Text #19

Max Range: 1.7819. Min Range: -1.7819

Max Act: 1.3244. Min Act: -0.0000

Data Index: 1106774 (C4 (Web Text))

Max Activating Token Index: 910