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

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

Neuron 162 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7209. Min Range: -3.7209

Max Act: 3.7209. Min Act: -0.1700

Data Index: 855642 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 3.7209. Min Range: -3.7209

Max Act: 3.7052. Min Act: -0.1700

Data Index: 34286 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 3.7209. Min Range: -3.7209

Max Act: 3.7052. Min Act: -0.1700

Data Index: 1348212 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 3.7209. Min Range: -3.7209

Max Act: 3.6426. Min Act: -0.1700

Data Index: 2984 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 3.7209. Min Range: -3.7209

Max Act: 3.6270. Min Act: -0.1700

Data Index: 100299 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 3.7209. Min Range: -3.7209

Max Act: 3.6426. Min Act: -0.1700

Data Index: 149555 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 3.7209. Min Range: -3.7209

Max Act: 3.6113. Min Act: -0.1700

Data Index: 643027 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 3.7209. Min Range: -3.7209

Max Act: 3.6113. Min Act: -0.1700

Data Index: 775285 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 3.7209. Min Range: -3.7209

Max Act: 3.6739. Min Act: -0.1700

Data Index: 171683 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 3.7209. Min Range: -3.7209

Max Act: 3.6426. Min Act: -0.1700

Data Index: 1136606 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 3.7209. Min Range: -3.7209

Max Act: 3.6426. Min Act: -0.1700

Data Index: 336196 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 3.7209. Min Range: -3.7209

Max Act: 3.6270. Min Act: -0.1700

Data Index: 399388 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 3.7209. Min Range: -3.7209

Max Act: 3.6583. Min Act: -0.1700

Data Index: 1344607 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 3.7209. Min Range: -3.7209

Max Act: 3.5800. Min Act: -0.1700

Data Index: 1197889 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 3.7209. Min Range: -3.7209

Max Act: 3.5487. Min Act: -0.1700

Data Index: 704394 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 3.7209. Min Range: -3.7209

Max Act: 3.5643. Min Act: -0.1700

Data Index: 64940 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 3.7209. Min Range: -3.7209

Max Act: 3.5487. Min Act: -0.1700

Data Index: 1175324 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 3.7209. Min Range: -3.7209

Max Act: 3.4703. Min Act: -0.1700

Data Index: 305065 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 3.7209. Min Range: -3.7209

Max Act: 3.5330. Min Act: -0.1700

Data Index: 368105 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 3.7209. Min Range: -3.7209

Max Act: 3.5173. Min Act: -0.1700

Data Index: 1097301 (C4 (Web Text))

Max Activating Token Index: 277