Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 861 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.7424. Min Act: -0.0003

Data Index: 1448251 (Python Code)

Max Activating Token Index: 145

Text #1

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6683. Min Act: -0.0003

Data Index: 1587099 (Python Code)

Max Activating Token Index: 407

Text #2

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6872. Min Act: -0.0003

Data Index: 1540785 (Python Code)

Max Activating Token Index: 177

Text #3

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.7000. Min Act: -0.0003

Data Index: 1599230 (Python Code)

Max Activating Token Index: 268

Text #4

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6933. Min Act: -0.0003

Data Index: 1425100 (Python Code)

Max Activating Token Index: 65

Text #5

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5958. Min Act: -0.0003

Data Index: 1378743 (Python Code)

Max Activating Token Index: 380

Text #6

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5975. Min Act: -0.0003

Data Index: 1656087 (Python Code)

Max Activating Token Index: 225

Text #7

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6898. Min Act: -0.0003

Data Index: 1373027 (Python Code)

Max Activating Token Index: 623

Text #8

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6500. Min Act: -0.0003

Data Index: 1595155 (Python Code)

Max Activating Token Index: 401

Text #9

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6268. Min Act: -0.0003

Data Index: 1597877 (Python Code)

Max Activating Token Index: 272

Text #10

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5682. Min Act: -0.0003

Data Index: 1597534 (Python Code)

Max Activating Token Index: 400

Text #11

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6714. Min Act: -0.0003

Data Index: 1367130 (Python Code)

Max Activating Token Index: 640

Text #12

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6241. Min Act: -0.0003

Data Index: 1599190 (Python Code)

Max Activating Token Index: 202

Text #13

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5396. Min Act: -0.0003

Data Index: 1574300 (Python Code)

Max Activating Token Index: 521

Text #14

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6169. Min Act: -0.0003

Data Index: 1436617 (Python Code)

Max Activating Token Index: 886

Text #15

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6285. Min Act: -0.0003

Data Index: 1400931 (Python Code)

Max Activating Token Index: 197

Text #16

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5989. Min Act: -0.0003

Data Index: 1392319 (Python Code)

Max Activating Token Index: 139

Text #17

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5985. Min Act: -0.0004

Data Index: 1509872 (Python Code)

Max Activating Token Index: 59

Text #18

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6590. Min Act: -0.0003

Data Index: 1368808 (Python Code)

Max Activating Token Index: 546

Text #19

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5562. Min Act: -0.0003

Data Index: 1521731 (Python Code)

Max Activating Token Index: 888