Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1459 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0003

Data Index: 962360 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0068. Min Act: -0.0004

Data Index: 909229 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0068. Min Act: -0.0004

Data Index: 545732 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0068. Min Act: -0.0004

Data Index: 704215 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0067. Min Act: -0.0004

Data Index: 957030 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0003

Data Index: 661377 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0003

Data Index: 196478 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0004

Data Index: 1224710 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0067. Min Act: -0.0004

Data Index: 781812 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0003

Data Index: 819018 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0004

Data Index: 324580 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0004

Data Index: 373549 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0003

Data Index: 1229590 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0004

Data Index: 857396 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0004

Data Index: 318177 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0004

Data Index: 694056 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0003

Data Index: 1321318 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0004

Data Index: 846481 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0004

Data Index: 1348812 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0004

Data Index: 696914 (C4 (Web Text))

Max Activating Token Index: 31