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

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

Neuron 2153 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: 3.0032. Min Range: -3.0032

Max Act: 2.8218. Min Act: -0.0000

Data Index: 1582416 (Python Code)

Max Activating Token Index: 527

Text #1

Max Range: 3.0032. Min Range: -3.0032

Max Act: 3.0032. Min Act: -0.0000

Data Index: 1444398 (Python Code)

Max Activating Token Index: 720

Text #2

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.4860. Min Act: -0.0000

Data Index: 787959 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.5995. Min Act: -0.0000

Data Index: 1404008 (Python Code)

Max Activating Token Index: 601

Text #4

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.5176. Min Act: -0.0000

Data Index: 1454688 (Python Code)

Max Activating Token Index: 574

Text #5

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.3961. Min Act: -0.0000

Data Index: 1171597 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.3668. Min Act: -0.0000

Data Index: 860841 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.2667. Min Act: -0.0000

Data Index: 1176315 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.2478. Min Act: -0.0000

Data Index: 1339008 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.0879. Min Act: -0.0000

Data Index: 225722 (C4 (Web Text))

Max Activating Token Index: 391

Text #10

Max Range: 3.0032. Min Range: -3.0032

Max Act: 1.9973. Min Act: -0.0000

Data Index: 884875 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.0184. Min Act: -0.0000

Data Index: 1110373 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.2044. Min Act: -0.0000

Data Index: 1541809 (Python Code)

Max Activating Token Index: 1000

Text #13

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.0437. Min Act: -0.0000

Data Index: 796548 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 3.0032. Min Range: -3.0032

Max Act: 1.8858. Min Act: -0.0000

Data Index: 1650643 (Python Code)

Max Activating Token Index: 422

Text #15

Max Range: 3.0032. Min Range: -3.0032

Max Act: 2.0357. Min Act: -0.0000

Data Index: 1183232 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 3.0032. Min Range: -3.0032

Max Act: 1.8778. Min Act: -0.0000

Data Index: 568368 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 3.0032. Min Range: -3.0032

Max Act: 1.8533. Min Act: -0.0000

Data Index: 526887 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 3.0032. Min Range: -3.0032

Max Act: 1.8511. Min Act: -0.0000

Data Index: 285841 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 3.0032. Min Range: -3.0032

Max Act: 1.8110. Min Act: -0.0000

Data Index: 210016 (C4 (Web Text))

Max Activating Token Index: 82