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

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

Neuron 1873 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: 5.1597. Min Range: -5.1597

Max Act: 5.1597. Min Act: -0.1700

Data Index: 191570 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 5.1597. Min Range: -5.1597

Max Act: 5.1597. Min Act: -0.1700

Data Index: 217560 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 5.1597. Min Range: -5.1597

Max Act: 5.1284. Min Act: -0.1700

Data Index: 1548311 (Python Code)

Max Activating Token Index: 367

Text #3

Max Range: 5.1597. Min Range: -5.1597

Max Act: 5.0972. Min Act: -0.1700

Data Index: 1406105 (Python Code)

Max Activating Token Index: 68

Text #4

Max Range: 5.1597. Min Range: -5.1597

Max Act: 5.0659. Min Act: -0.1700

Data Index: 342446 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 5.1597. Min Range: -5.1597

Max Act: 5.0659. Min Act: -0.1700

Data Index: 1082475 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 5.1597. Min Range: -5.1597

Max Act: 5.0034. Min Act: -0.1700

Data Index: 442486 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 5.1597. Min Range: -5.1597

Max Act: 5.0659. Min Act: -0.1700

Data Index: 1034216 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 5.1597. Min Range: -5.1597

Max Act: 5.0347. Min Act: -0.1700

Data Index: 287237 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 5.1597. Min Range: -5.1597

Max Act: 5.0347. Min Act: -0.1700

Data Index: 543558 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 5.1597. Min Range: -5.1597

Max Act: 4.9722. Min Act: -0.1700

Data Index: 1528295 (Python Code)

Max Activating Token Index: 210

Text #11

Max Range: 5.1597. Min Range: -5.1597

Max Act: 4.9722. Min Act: -0.1700

Data Index: 1116704 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 5.1597. Min Range: -5.1597

Max Act: 4.9409. Min Act: -0.1700

Data Index: 179489 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 5.1597. Min Range: -5.1597

Max Act: 4.9409. Min Act: -0.1700

Data Index: 930397 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 5.1597. Min Range: -5.1597

Max Act: 4.9097. Min Act: -0.1700

Data Index: 1615996 (Python Code)

Max Activating Token Index: 61

Text #15

Max Range: 5.1597. Min Range: -5.1597

Max Act: 5.0034. Min Act: -0.1700

Data Index: 1112978 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 5.1597. Min Range: -5.1597

Max Act: 5.0034. Min Act: -0.1700

Data Index: 559395 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 5.1597. Min Range: -5.1597

Max Act: 4.9409. Min Act: -0.1700

Data Index: 122175 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 5.1597. Min Range: -5.1597

Max Act: 4.9409. Min Act: -0.1700

Data Index: 714826 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 5.1597. Min Range: -5.1597

Max Act: 4.9722. Min Act: -0.1700

Data Index: 1264680 (C4 (Web Text))

Max Activating Token Index: 502