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

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

Neuron 21 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: 3.6890. Min Range: -3.6890

Max Act: 3.6890. Min Act: -0.1700

Data Index: 664036 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 3.6890. Min Range: -3.6890

Max Act: 3.5795. Min Act: -0.1700

Data Index: 1223751 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 3.6890. Min Range: -3.6890

Max Act: 3.5638. Min Act: -0.1700

Data Index: 116103 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 3.6890. Min Range: -3.6890

Max Act: 3.5638. Min Act: -0.1700

Data Index: 418986 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 3.6890. Min Range: -3.6890

Max Act: 3.5168. Min Act: -0.1700

Data Index: 681046 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 3.6890. Min Range: -3.6890

Max Act: 3.4855. Min Act: -0.1700

Data Index: 884259 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 3.6890. Min Range: -3.6890

Max Act: 3.5011. Min Act: -0.1700

Data Index: 1126517 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 3.6890. Min Range: -3.6890

Max Act: 3.4698. Min Act: -0.1700

Data Index: 1335233 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 3.6890. Min Range: -3.6890

Max Act: 3.4698. Min Act: -0.1700

Data Index: 1120953 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 3.6890. Min Range: -3.6890

Max Act: 3.4385. Min Act: -0.1700

Data Index: 798157 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 3.6890. Min Range: -3.6890

Max Act: 3.4541. Min Act: -0.1700

Data Index: 533768 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 3.6890. Min Range: -3.6890

Max Act: 3.4541. Min Act: -0.1700

Data Index: 783952 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 3.6890. Min Range: -3.6890

Max Act: 3.4541. Min Act: -0.1700

Data Index: 145914 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 3.6890. Min Range: -3.6890

Max Act: 3.4385. Min Act: -0.1700

Data Index: 214174 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 3.6890. Min Range: -3.6890

Max Act: 3.4385. Min Act: -0.1700

Data Index: 662588 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 3.6890. Min Range: -3.6890

Max Act: 3.4385. Min Act: -0.1700

Data Index: 552355 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 3.6890. Min Range: -3.6890

Max Act: 3.4385. Min Act: -0.1700

Data Index: 154804 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 3.6890. Min Range: -3.6890

Max Act: 3.4228. Min Act: -0.1700

Data Index: 891300 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 3.6890. Min Range: -3.6890

Max Act: 3.4071. Min Act: -0.1700

Data Index: 711139 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 3.6890. Min Range: -3.6890

Max Act: 3.4071. Min Act: -0.1700

Data Index: 880911 (C4 (Web Text))

Max Activating Token Index: 728