Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1664 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.7075. Min Range: -5.7075

Max Act: 5.7075. Min Act: -0.1700

Data Index: 160730 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 5.7075. Min Range: -5.7075

Max Act: 5.5825. Min Act: -0.1700

Data Index: 1223471 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 5.7075. Min Range: -5.7075

Max Act: 5.4888. Min Act: -0.1700

Data Index: 1163802 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 5.7075. Min Range: -5.7075

Max Act: 5.4888. Min Act: -0.1700

Data Index: 322090 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 5.7075. Min Range: -5.7075

Max Act: 5.3325. Min Act: -0.1700

Data Index: 1038412 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 5.7075. Min Range: -5.7075

Max Act: 5.3325. Min Act: -0.1699

Data Index: 591041 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 5.7075. Min Range: -5.7075

Max Act: 5.3325. Min Act: -0.1700

Data Index: 1049075 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 5.7075. Min Range: -5.7075

Max Act: 5.3013. Min Act: -0.1700

Data Index: 930113 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 5.7075. Min Range: -5.7075

Max Act: 5.3325. Min Act: -0.1700

Data Index: 564049 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 5.7075. Min Range: -5.7075

Max Act: 5.2700. Min Act: -0.1700

Data Index: 1247610 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 5.7075. Min Range: -5.7075

Max Act: 5.2388. Min Act: -0.1700

Data Index: 698663 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 5.7075. Min Range: -5.7075

Max Act: 5.2075. Min Act: -0.1699

Data Index: 192019 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 5.7075. Min Range: -5.7075

Max Act: 5.2075. Min Act: -0.1700

Data Index: 6164 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 5.7075. Min Range: -5.7075

Max Act: 5.1763. Min Act: -0.1700

Data Index: 784336 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 5.7075. Min Range: -5.7075

Max Act: 5.2388. Min Act: -0.1700

Data Index: 466417 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 5.7075. Min Range: -5.7075

Max Act: 5.2075. Min Act: -0.1699

Data Index: 1054068 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 5.7075. Min Range: -5.7075

Max Act: 5.2075. Min Act: -0.1700

Data Index: 599537 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 5.7075. Min Range: -5.7075

Max Act: 5.1450. Min Act: -0.1700

Data Index: 567273 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 5.7075. Min Range: -5.7075

Max Act: 5.1450. Min Act: -0.1700

Data Index: 267510 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 5.7075. Min Range: -5.7075

Max Act: 5.1138. Min Act: -0.1698

Data Index: 934770 (C4 (Web Text))

Max Activating Token Index: 240