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

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

Neuron 1304 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: 5.6989. Min Range: -5.6989

Max Act: 5.6989. Min Act: -0.1700

Data Index: 1120714 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 5.6989. Min Range: -5.6989

Max Act: 5.4802. Min Act: -0.1700

Data Index: 1172691 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 5.6989. Min Range: -5.6989

Max Act: 5.2614. Min Act: -0.1700

Data Index: 774452 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 5.6989. Min Range: -5.6989

Max Act: 5.2302. Min Act: -0.1700

Data Index: 509716 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 5.6989. Min Range: -5.6989

Max Act: 5.1677. Min Act: -0.1700

Data Index: 615428 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 5.6989. Min Range: -5.6989

Max Act: 5.0739. Min Act: -0.1700

Data Index: 195815 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 5.6989. Min Range: -5.6989

Max Act: 5.1052. Min Act: -0.1700

Data Index: 966334 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 5.6989. Min Range: -5.6989

Max Act: 5.0427. Min Act: -0.1700

Data Index: 49823 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 5.6989. Min Range: -5.6989

Max Act: 5.0739. Min Act: -0.1700

Data Index: 679446 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 5.6989. Min Range: -5.6989

Max Act: 5.0114. Min Act: -0.1700

Data Index: 543729 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 5.6989. Min Range: -5.6989

Max Act: 5.0114. Min Act: -0.1700

Data Index: 25167 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 5.6989. Min Range: -5.6989

Max Act: 5.1364. Min Act: -0.1700

Data Index: 1123315 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 5.6989. Min Range: -5.6989

Max Act: 5.0114. Min Act: -0.1700

Data Index: 616882 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 5.6989. Min Range: -5.6989

Max Act: 5.0114. Min Act: -0.1700

Data Index: 28975 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 5.6989. Min Range: -5.6989

Max Act: 5.0427. Min Act: -0.1700

Data Index: 673508 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 5.6989. Min Range: -5.6989

Max Act: 5.0427. Min Act: -0.1700

Data Index: 746352 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 5.6989. Min Range: -5.6989

Max Act: 5.0114. Min Act: -0.1700

Data Index: 476840 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 5.6989. Min Range: -5.6989

Max Act: 5.0739. Min Act: -0.1700

Data Index: 888356 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 5.6989. Min Range: -5.6989

Max Act: 4.9802. Min Act: -0.1700

Data Index: 668285 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 5.6989. Min Range: -5.6989

Max Act: 5.0114. Min Act: -0.1700

Data Index: 427106 (C4 (Web Text))

Max Activating Token Index: 269