Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4150 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.4783. Min Act: -0.0000

Data Index: 1577471 (Python Code)

Max Activating Token Index: 101

Text #1

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.3005. Min Act: -0.0000

Data Index: 1545512 (Python Code)

Max Activating Token Index: 25

Text #2

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.3482. Min Act: -0.0000

Data Index: 1354429 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.5334. Min Act: -0.0000

Data Index: 1362342 (Python Code)

Max Activating Token Index: 1009

Text #4

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.3018. Min Act: -0.0000

Data Index: 1471388 (Python Code)

Max Activating Token Index: 258

Text #5

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.3919. Min Act: -0.0000

Data Index: 1420074 (Python Code)

Max Activating Token Index: 36

Text #6

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.2650. Min Act: -0.0000

Data Index: 215153 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.1458. Min Act: -0.0000

Data Index: 1596630 (Python Code)

Max Activating Token Index: 103

Text #8

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.2719. Min Act: -0.0000

Data Index: 1544905 (Python Code)

Max Activating Token Index: 949

Text #9

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.2142. Min Act: -0.0000

Data Index: 1577277 (Python Code)

Max Activating Token Index: 680

Text #10

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.2162. Min Act: -0.0000

Data Index: 1554960 (Python Code)

Max Activating Token Index: 1015

Text #11

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.2157. Min Act: -0.0000

Data Index: 1603222 (Python Code)

Max Activating Token Index: 300

Text #12

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.0634. Min Act: -0.0000

Data Index: 1576513 (Python Code)

Max Activating Token Index: 916

Text #13

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.1172. Min Act: -0.0000

Data Index: 697219 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.0913. Min Act: -0.0000

Data Index: 1366851 (Python Code)

Max Activating Token Index: 728

Text #15

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.3149. Min Act: -0.0000

Data Index: 1602901 (Python Code)

Max Activating Token Index: 132

Text #16

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.1630. Min Act: -0.0000

Data Index: 1633126 (Python Code)

Max Activating Token Index: 172

Text #17

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.1354. Min Act: -0.0000

Data Index: 320524 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.1255. Min Act: -0.0000

Data Index: 183164 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.1612. Min Act: -0.0000

Data Index: 1510850 (Python Code)

Max Activating Token Index: 589