Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 721 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.5252. Min Range: -3.5252

Max Act: 3.5252. Min Act: -0.1700

Data Index: 1113768 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 3.5252. Min Range: -3.5252

Max Act: 3.4839. Min Act: -0.1700

Data Index: 508480 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 3.5252. Min Range: -3.5252

Max Act: 3.4669. Min Act: -0.1700

Data Index: 77369 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 3.5252. Min Range: -3.5252

Max Act: 3.4412. Min Act: -0.1699

Data Index: 139051 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 3.5252. Min Range: -3.5252

Max Act: 3.4297. Min Act: -0.1699

Data Index: 204599 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 3.5252. Min Range: -3.5252

Max Act: 3.3977. Min Act: -0.1700

Data Index: 1014353 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 3.5252. Min Range: -3.5252

Max Act: 3.3762. Min Act: -0.1522

Data Index: 1608092 (Python Code)

Max Activating Token Index: 67

Text #7

Max Range: 3.5252. Min Range: -3.5252

Max Act: 3.3737. Min Act: -0.1625

Data Index: 651968 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 3.5252. Min Range: -3.5252

Max Act: 3.3581. Min Act: -0.1700

Data Index: 533661 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 3.5252. Min Range: -3.5252

Max Act: 3.3597. Min Act: -0.1626

Data Index: 1161327 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 3.5252. Min Range: -3.5252

Max Act: 3.3372. Min Act: -0.1700

Data Index: 639478 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 3.5252. Min Range: -3.5252

Max Act: 3.3213. Min Act: -0.1535

Data Index: 609918 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 3.5252. Min Range: -3.5252

Max Act: 3.3401. Min Act: -0.1700

Data Index: 255116 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 3.5252. Min Range: -3.5252

Max Act: 3.3105. Min Act: -0.1700

Data Index: 167555 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 3.5252. Min Range: -3.5252

Max Act: 3.3142. Min Act: -0.1700

Data Index: 175938 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 3.5252. Min Range: -3.5252

Max Act: 3.3078. Min Act: -0.1700

Data Index: 342867 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 3.5252. Min Range: -3.5252

Max Act: 3.3086. Min Act: -0.1700

Data Index: 1011556 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 3.5252. Min Range: -3.5252

Max Act: 3.2945. Min Act: -0.1700

Data Index: 230043 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 3.5252. Min Range: -3.5252

Max Act: 3.2994. Min Act: -0.1627

Data Index: 830357 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 3.5252. Min Range: -3.5252

Max Act: 3.2943. Min Act: -0.1700

Data Index: 1003929 (C4 (Web Text))

Max Activating Token Index: 158