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

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

Neuron 846 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: 3.8931. Min Range: -3.8931

Max Act: 3.8931. Min Act: -0.1700

Data Index: 1037566 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.7054. Min Act: -0.1700

Data Index: 17459 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.7054. Min Act: -0.1700

Data Index: 710716 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.6741. Min Act: -0.1700

Data Index: 1346115 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.6428. Min Act: -0.1700

Data Index: 77376 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.6115. Min Act: -0.1700

Data Index: 561438 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.6428. Min Act: -0.1700

Data Index: 290845 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.6428. Min Act: -0.1700

Data Index: 735669 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.5802. Min Act: -0.1697

Data Index: 354471 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.5488. Min Act: -0.1700

Data Index: 1551403 (Python Code)

Max Activating Token Index: 707

Text #10

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.5488. Min Act: -0.1699

Data Index: 173640 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.5802. Min Act: -0.1700

Data Index: 757716 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.5802. Min Act: -0.1700

Data Index: 854699 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.5175. Min Act: -0.1700

Data Index: 958885 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.5488. Min Act: -0.1700

Data Index: 861932 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.5175. Min Act: -0.1700

Data Index: 33471 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.5175. Min Act: -0.1700

Data Index: 352540 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.5488. Min Act: -0.1700

Data Index: 938821 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.5175. Min Act: -0.1700

Data Index: 1351851 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 3.8931. Min Range: -3.8931

Max Act: 3.5175. Min Act: -0.1700

Data Index: 905325 (C4 (Web Text))

Max Activating Token Index: 820