Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 943 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.4047. Min Range: -5.4047

Max Act: 5.4047. Min Act: -0.1700

Data Index: 243944 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 5.4047. Min Range: -5.4047

Max Act: 5.1235. Min Act: -0.1700

Data Index: 1249327 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 5.4047. Min Range: -5.4047

Max Act: 5.2485. Min Act: -0.1700

Data Index: 171383 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 5.4047. Min Range: -5.4047

Max Act: 5.1547. Min Act: -0.1700

Data Index: 566334 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 5.4047. Min Range: -5.4047

Max Act: 5.1547. Min Act: -0.1700

Data Index: 1159272 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 5.4047. Min Range: -5.4047

Max Act: 5.0922. Min Act: -0.1700

Data Index: 939060 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 5.4047. Min Range: -5.4047

Max Act: 5.0922. Min Act: -0.1700

Data Index: 696229 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 5.4047. Min Range: -5.4047

Max Act: 5.0922. Min Act: -0.1700

Data Index: 767632 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 5.4047. Min Range: -5.4047

Max Act: 5.1235. Min Act: -0.1700

Data Index: 1351710 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 5.4047. Min Range: -5.4047

Max Act: 5.0297. Min Act: -0.1700

Data Index: 412610 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 5.4047. Min Range: -5.4047

Max Act: 5.0297. Min Act: -0.1700

Data Index: 129096 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 5.4047. Min Range: -5.4047

Max Act: 5.0922. Min Act: -0.1700

Data Index: 576910 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 5.4047. Min Range: -5.4047

Max Act: 5.0297. Min Act: -0.1700

Data Index: 1330234 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 5.4047. Min Range: -5.4047

Max Act: 4.9985. Min Act: -0.1700

Data Index: 1162023 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 5.4047. Min Range: -5.4047

Max Act: 5.0297. Min Act: -0.1700

Data Index: 715737 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 5.4047. Min Range: -5.4047

Max Act: 5.1235. Min Act: -0.1700

Data Index: 1050294 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 5.4047. Min Range: -5.4047

Max Act: 4.9985. Min Act: -0.1700

Data Index: 158495 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 5.4047. Min Range: -5.4047

Max Act: 5.0610. Min Act: -0.1700

Data Index: 1244311 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 5.4047. Min Range: -5.4047

Max Act: 4.9672. Min Act: -0.1700

Data Index: 439203 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 5.4047. Min Range: -5.4047

Max Act: 5.0610. Min Act: -0.1700

Data Index: 740011 (C4 (Web Text))

Max Activating Token Index: 552