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

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

Neuron 1820 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.8504. Min Act: -0.0002

Data Index: 92240 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7330. Min Act: -0.0001

Data Index: 1284164 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7371. Min Act: -0.0002

Data Index: 509068 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7217. Min Act: -0.0001

Data Index: 810874 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7077. Min Act: -0.0002

Data Index: 673609 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7052. Min Act: -0.0001

Data Index: 29354 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7258. Min Act: -0.0001

Data Index: 1288213 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7034. Min Act: -0.0002

Data Index: 709716 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7024. Min Act: -0.0001

Data Index: 728123 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7156. Min Act: -0.0002

Data Index: 1200352 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6796. Min Act: -0.0002

Data Index: 21554 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7039. Min Act: -0.0001

Data Index: 371293 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6980. Min Act: -0.0001

Data Index: 999270 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6717. Min Act: -0.0002

Data Index: 38979 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6764. Min Act: -0.0002

Data Index: 1055335 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6934. Min Act: -0.0002

Data Index: 889308 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6873. Min Act: -0.0001

Data Index: 644923 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6784. Min Act: -0.0001

Data Index: 819646 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6827. Min Act: -0.0001

Data Index: 1289757 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6827. Min Act: -0.0001

Data Index: 826040 (C4 (Web Text))

Max Activating Token Index: 294