Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1085 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.2975. Min Act: -0.1700

Data Index: 1277758 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.3132. Min Act: -0.1700

Data Index: 348666 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.2661. Min Act: -0.1700

Data Index: 1267064 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.2503. Min Act: -0.1700

Data Index: 1329278 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.2189. Min Act: -0.1700

Data Index: 416957 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.2032. Min Act: -0.1700

Data Index: 746987 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.2189. Min Act: -0.1700

Data Index: 899796 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.1874. Min Act: -0.1700

Data Index: 1340621 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.1874. Min Act: -0.1700

Data Index: 171978 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.1874. Min Act: -0.1700

Data Index: 823144 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.1874. Min Act: -0.1700

Data Index: 573468 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.1874. Min Act: -0.1700

Data Index: 339830 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.1717. Min Act: -0.1700

Data Index: 1354022 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.1717. Min Act: -0.1700

Data Index: 297857 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.1559. Min Act: -0.1700

Data Index: 837593 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.1559. Min Act: -0.1700

Data Index: 169310 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.1559. Min Act: -0.1700

Data Index: 1288009 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.1559. Min Act: -0.1700

Data Index: 974009 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.1559. Min Act: -0.1700

Data Index: 718546 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.1559. Min Act: -0.1700

Data Index: 700785 (C4 (Web Text))

Max Activating Token Index: 192