Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 750 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.3899. Min Act: -0.1700

Data Index: 497024 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.2329. Min Act: -0.1700

Data Index: 29912 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.2172. Min Act: -0.1700

Data Index: 70952 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.2014. Min Act: -0.1700

Data Index: 178361 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.1700. Min Act: -0.1700

Data Index: 242940 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.1385. Min Act: -0.1700

Data Index: 400627 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.1385. Min Act: -0.1700

Data Index: 447164 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.1227. Min Act: -0.1700

Data Index: 557567 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.1227. Min Act: -0.1700

Data Index: 271955 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.0912. Min Act: -0.1700

Data Index: 29570 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.0596. Min Act: -0.1700

Data Index: 622416 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.0754. Min Act: -0.1700

Data Index: 48285 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.1542. Min Act: -0.1700

Data Index: 1283776 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.1070. Min Act: -0.1700

Data Index: 970413 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.0912. Min Act: -0.1700

Data Index: 1141523 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.0754. Min Act: -0.1700

Data Index: 600280 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.0912. Min Act: -0.1700

Data Index: 261134 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.0754. Min Act: -0.1700

Data Index: 1205646 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.0754. Min Act: -0.1700

Data Index: 1204318 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.0912. Min Act: -0.1700

Data Index: 1179012 (C4 (Web Text))

Max Activating Token Index: 628