Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5215 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.1240. Min Range: -3.1240

Max Act: 3.0688. Min Act: -0.0000

Data Index: 1029079 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 3.1240. Min Range: -3.1240

Max Act: 3.1240. Min Act: -0.0000

Data Index: 5202 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 3.1240. Min Range: -3.1240

Max Act: 3.0065. Min Act: -0.0000

Data Index: 168323 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 3.1240. Min Range: -3.1240

Max Act: 2.7616. Min Act: -0.0000

Data Index: 951239 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 3.1240. Min Range: -3.1240

Max Act: 2.4226. Min Act: -0.0000

Data Index: 931138 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 3.1240. Min Range: -3.1240

Max Act: 2.5118. Min Act: -0.0000

Data Index: 1019245 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 3.1240. Min Range: -3.1240

Max Act: 2.3587. Min Act: -0.0000

Data Index: 277264 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 3.1240. Min Range: -3.1240

Max Act: 2.4775. Min Act: -0.0000

Data Index: 5709 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 3.1240. Min Range: -3.1240

Max Act: 2.2030. Min Act: -0.0000

Data Index: 1178465 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 3.1240. Min Range: -3.1240

Max Act: 2.4465. Min Act: -0.0000

Data Index: 250435 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 3.1240. Min Range: -3.1240

Max Act: 2.6937. Min Act: -0.0000

Data Index: 1041952 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 3.1240. Min Range: -3.1240

Max Act: 2.5110. Min Act: -0.0000

Data Index: 1649656 (Python Code)

Max Activating Token Index: 688

Text #12

Max Range: 3.1240. Min Range: -3.1240

Max Act: 2.2513. Min Act: -0.0000

Data Index: 910463 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 3.1240. Min Range: -3.1240

Max Act: 2.6154. Min Act: -0.0000

Data Index: 1157504 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 3.1240. Min Range: -3.1240

Max Act: 2.1300. Min Act: -0.0000

Data Index: 107432 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 3.1240. Min Range: -3.1240

Max Act: 2.1061. Min Act: -0.0000

Data Index: 702327 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 3.1240. Min Range: -3.1240

Max Act: 2.1109. Min Act: -0.0000

Data Index: 1270839 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 3.1240. Min Range: -3.1240

Max Act: 2.8519. Min Act: -0.0000

Data Index: 1330423 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 3.1240. Min Range: -3.1240

Max Act: 2.6038. Min Act: -0.0000

Data Index: 1641430 (Python Code)

Max Activating Token Index: 580

Text #19

Max Range: 3.1240. Min Range: -3.1240

Max Act: 2.1891. Min Act: -0.0000

Data Index: 1308028 (C4 (Web Text))

Max Activating Token Index: 425