Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 689 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0056. Min Act: -0.0006

Data Index: 1519093 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0055. Min Act: -0.0005

Data Index: 1652866 (Python Code)

Max Activating Token Index: 452

Text #2

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0054. Min Act: -0.0005

Data Index: 946408 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0054. Min Act: -0.0006

Data Index: 538212 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0051. Min Act: -0.0006

Data Index: 1469177 (Python Code)

Max Activating Token Index: 208

Text #5

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0050. Min Act: -0.0006

Data Index: 455946 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0049. Min Act: -0.0006

Data Index: 379923 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0048. Min Act: -0.0005

Data Index: 1626353 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0046. Min Act: -0.0006

Data Index: 1606119 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0046. Min Act: -0.0005

Data Index: 410729 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0046. Min Act: -0.0006

Data Index: 16201 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0047. Min Act: -0.0006

Data Index: 717320 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0047. Min Act: -0.0006

Data Index: 79646 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0045. Min Act: -0.0006

Data Index: 410765 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0045. Min Act: -0.0006

Data Index: 603918 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0045. Min Act: -0.0006

Data Index: 93529 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0045. Min Act: -0.0006

Data Index: 1323054 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0044. Min Act: -0.0006

Data Index: 644381 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0046. Min Act: -0.0006

Data Index: 326301 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 0.0056. Min Range: -0.0056

Max Act: 0.0044. Min Act: -0.0006

Data Index: 1606321 (Python Code)

Max Activating Token Index: 302