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

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

Neuron 995 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5882. Min Range: -3.5882

Max Act: 3.5882. Min Act: -0.1700

Data Index: 877118 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 3.5882. Min Range: -3.5882

Max Act: 3.5256. Min Act: -0.1700

Data Index: 286084 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 3.5882. Min Range: -3.5882

Max Act: 3.5256. Min Act: -0.1700

Data Index: 455654 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 3.5882. Min Range: -3.5882

Max Act: 3.4942. Min Act: -0.1700

Data Index: 1217532 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 3.5882. Min Range: -3.5882

Max Act: 3.4629. Min Act: -0.1700

Data Index: 305673 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 3.5882. Min Range: -3.5882

Max Act: 3.4942. Min Act: -0.1700

Data Index: 958254 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 3.5882. Min Range: -3.5882

Max Act: 3.4942. Min Act: -0.1700

Data Index: 476577 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 3.5882. Min Range: -3.5882

Max Act: 3.5256. Min Act: -0.1700

Data Index: 518515 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 3.5882. Min Range: -3.5882

Max Act: 3.4629. Min Act: -0.1700

Data Index: 1054106 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 3.5882. Min Range: -3.5882

Max Act: 3.4315. Min Act: -0.1700

Data Index: 1232384 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 3.5882. Min Range: -3.5882

Max Act: 3.4629. Min Act: -0.1700

Data Index: 588260 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 3.5882. Min Range: -3.5882

Max Act: 3.4629. Min Act: -0.1700

Data Index: 383624 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 3.5882. Min Range: -3.5882

Max Act: 3.4629. Min Act: -0.1700

Data Index: 61427 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 3.5882. Min Range: -3.5882

Max Act: 3.5569. Min Act: -0.1700

Data Index: 476021 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 3.5882. Min Range: -3.5882

Max Act: 3.4629. Min Act: -0.1700

Data Index: 102342 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 3.5882. Min Range: -3.5882

Max Act: 3.4002. Min Act: -0.1700

Data Index: 379073 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 3.5882. Min Range: -3.5882

Max Act: 3.4315. Min Act: -0.1700

Data Index: 1242270 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 3.5882. Min Range: -3.5882

Max Act: 3.4629. Min Act: -0.1700

Data Index: 219712 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 3.5882. Min Range: -3.5882

Max Act: 3.4002. Min Act: -0.1700

Data Index: 1164752 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 3.5882. Min Range: -3.5882

Max Act: 3.3374. Min Act: -0.1700

Data Index: 455396 (C4 (Web Text))

Max Activating Token Index: 644