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

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

Neuron 2301 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: 0.0048. Min Range: -0.0048

Max Act: 0.0048. Min Act: -0.0004

Data Index: 65073 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0047. Min Act: -0.0003

Data Index: 453527 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0004

Data Index: 612216 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0045. Min Act: -0.0003

Data Index: 283834 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0043. Min Act: -0.0004

Data Index: 362399 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0043. Min Act: -0.0004

Data Index: 146520 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0042. Min Act: -0.0004

Data Index: 833384 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0042. Min Act: -0.0003

Data Index: 1610130 (Python Code)

Max Activating Token Index: 725

Text #8

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0043. Min Act: -0.0003

Data Index: 1298120 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0042. Min Act: -0.0003

Data Index: 1596318 (Python Code)

Max Activating Token Index: 622

Text #10

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0042. Min Act: -0.0004

Data Index: 275638 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0042. Min Act: -0.0004

Data Index: 590700 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0042. Min Act: -0.0004

Data Index: 983045 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0042. Min Act: -0.0003

Data Index: 357351 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0041. Min Act: -0.0003

Data Index: 307600 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0041. Min Act: -0.0003

Data Index: 784479 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0041. Min Act: -0.0003

Data Index: 1553389 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0041. Min Act: -0.0003

Data Index: 1412627 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0041. Min Act: -0.0004

Data Index: 1554428 (Python Code)

Max Activating Token Index: 1

Text #19

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0041. Min Act: -0.0003

Data Index: 1456457 (Python Code)

Max Activating Token Index: 1