Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1999 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0183. Min Act: -0.0006

Data Index: 1505568 (Python Code)

Max Activating Token Index: 899

Text #1

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0176. Min Act: -0.0006

Data Index: 1503650 (Python Code)

Max Activating Token Index: 576

Text #2

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0169. Min Act: -0.0006

Data Index: 1613895 (Python Code)

Max Activating Token Index: 519

Text #3

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0164. Min Act: -0.0006

Data Index: 1364245 (Python Code)

Max Activating Token Index: 771

Text #4

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0160. Min Act: -0.0006

Data Index: 1389525 (Python Code)

Max Activating Token Index: 650

Text #5

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0167. Min Act: -0.0006

Data Index: 1490461 (Python Code)

Max Activating Token Index: 622

Text #6

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0170. Min Act: -0.0006

Data Index: 1641511 (Python Code)

Max Activating Token Index: 1006

Text #7

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0167. Min Act: -0.0006

Data Index: 1483672 (Python Code)

Max Activating Token Index: 888

Text #8

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0166. Min Act: -0.0006

Data Index: 1518979 (Python Code)

Max Activating Token Index: 289

Text #9

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0155. Min Act: -0.0006

Data Index: 1546173 (Python Code)

Max Activating Token Index: 992

Text #10

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0162. Min Act: -0.0006

Data Index: 1582403 (Python Code)

Max Activating Token Index: 797

Text #11

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0162. Min Act: -0.0006

Data Index: 1500313 (Python Code)

Max Activating Token Index: 662

Text #12

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0164. Min Act: -0.0006

Data Index: 1575380 (Python Code)

Max Activating Token Index: 667

Text #13

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0157. Min Act: -0.0006

Data Index: 1390916 (Python Code)

Max Activating Token Index: 268

Text #14

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0160. Min Act: -0.0006

Data Index: 1537534 (Python Code)

Max Activating Token Index: 720

Text #15

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0156. Min Act: -0.0006

Data Index: 1360814 (Python Code)

Max Activating Token Index: 956

Text #16

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0158. Min Act: -0.0006

Data Index: 1618223 (Python Code)

Max Activating Token Index: 962

Text #17

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0166. Min Act: -0.0006

Data Index: 1621579 (Python Code)

Max Activating Token Index: 566

Text #18

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0166. Min Act: -0.0006

Data Index: 1463558 (Python Code)

Max Activating Token Index: 93

Text #19

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0155. Min Act: -0.0006

Data Index: 1485471 (Python Code)

Max Activating Token Index: 884