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

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

Neuron 1472 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0740. Min Range: -1.0740

Max Act: 1.0740. Min Act: -0.0001

Data Index: 1416589 (Python Code)

Max Activating Token Index: 85

Text #1

Max Range: 1.0740. Min Range: -1.0740

Max Act: 1.0217. Min Act: -0.0001

Data Index: 1510429 (Python Code)

Max Activating Token Index: 19

Text #2

Max Range: 1.0740. Min Range: -1.0740

Max Act: 1.0106. Min Act: -0.0001

Data Index: 1447796 (Python Code)

Max Activating Token Index: 389

Text #3

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.9427. Min Act: -0.0001

Data Index: 1597439 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.8347. Min Act: -0.0001

Data Index: 1628807 (Python Code)

Max Activating Token Index: 161

Text #5

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.8632. Min Act: -0.0001

Data Index: 1372283 (Python Code)

Max Activating Token Index: 332

Text #6

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.9323. Min Act: -0.0001

Data Index: 1590848 (Python Code)

Max Activating Token Index: 471

Text #7

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.8908. Min Act: -0.0001

Data Index: 1543478 (Python Code)

Max Activating Token Index: 59

Text #8

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.8159. Min Act: -0.0001

Data Index: 1655254 (Python Code)

Max Activating Token Index: 378

Text #9

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.8130. Min Act: -0.0001

Data Index: 1549554 (Python Code)

Max Activating Token Index: 160

Text #10

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.8320. Min Act: -0.0001

Data Index: 1608394 (Python Code)

Max Activating Token Index: 264

Text #11

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.8462. Min Act: -0.0001

Data Index: 1375481 (Python Code)

Max Activating Token Index: 243

Text #12

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.8106. Min Act: -0.0001

Data Index: 1380244 (Python Code)

Max Activating Token Index: 888

Text #13

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.8057. Min Act: -0.0001

Data Index: 22984 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.8077. Min Act: -0.0001

Data Index: 1062001 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.7813. Min Act: -0.0001

Data Index: 1601697 (Python Code)

Max Activating Token Index: 41

Text #16

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.7784. Min Act: -0.0001

Data Index: 1466850 (Python Code)

Max Activating Token Index: 621

Text #17

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.7280. Min Act: -0.0001

Data Index: 1373671 (Python Code)

Max Activating Token Index: 231

Text #18

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.8446. Min Act: -0.0001

Data Index: 1619505 (Python Code)

Max Activating Token Index: 504

Text #19

Max Range: 1.0740. Min Range: -1.0740

Max Act: 0.7485. Min Act: -0.0001

Data Index: 1182371 (C4 (Web Text))

Max Activating Token Index: 245