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

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

Neuron 1941 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1615. Min Range: -3.1615

Max Act: 3.1615. Min Act: -0.1700

Data Index: 1042816 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 3.1615. Min Range: -3.1615

Max Act: 3.0196. Min Act: -0.1700

Data Index: 1145527 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 3.1615. Min Range: -3.1615

Max Act: 2.9880. Min Act: -0.1700

Data Index: 16112 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 3.1615. Min Range: -3.1615

Max Act: 2.9880. Min Act: -0.1700

Data Index: 384911 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 3.1615. Min Range: -3.1615

Max Act: 2.9563. Min Act: -0.1700

Data Index: 411278 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 3.1615. Min Range: -3.1615

Max Act: 2.9405. Min Act: -0.1700

Data Index: 1057523 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 3.1615. Min Range: -3.1615

Max Act: 2.9088. Min Act: -0.1700

Data Index: 780732 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 3.1615. Min Range: -3.1615

Max Act: 2.9246. Min Act: -0.1700

Data Index: 399452 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 3.1615. Min Range: -3.1615

Max Act: 2.9088. Min Act: -0.1700

Data Index: 631183 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 3.1615. Min Range: -3.1615

Max Act: 2.9088. Min Act: -0.1700

Data Index: 1332344 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 3.1615. Min Range: -3.1615

Max Act: 2.8771. Min Act: -0.1700

Data Index: 484093 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 3.1615. Min Range: -3.1615

Max Act: 2.8453. Min Act: -0.1700

Data Index: 818854 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 3.1615. Min Range: -3.1615

Max Act: 2.8453. Min Act: -0.1700

Data Index: 371798 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 3.1615. Min Range: -3.1615

Max Act: 2.8771. Min Act: -0.1700

Data Index: 314650 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 3.1615. Min Range: -3.1615

Max Act: 2.8453. Min Act: -0.1700

Data Index: 128260 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 3.1615. Min Range: -3.1615

Max Act: 2.8453. Min Act: -0.1700

Data Index: 504795 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 3.1615. Min Range: -3.1615

Max Act: 2.8453. Min Act: -0.1700

Data Index: 288432 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 3.1615. Min Range: -3.1615

Max Act: 2.8453. Min Act: -0.1700

Data Index: 591455 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 3.1615. Min Range: -3.1615

Max Act: 2.8294. Min Act: -0.1700

Data Index: 1044944 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 3.1615. Min Range: -3.1615

Max Act: 2.8294. Min Act: -0.1700

Data Index: 1053001 (C4 (Web Text))

Max Activating Token Index: 336