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

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

Neuron 1953 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: 5.9236. Min Range: -5.9236

Max Act: 5.8924. Min Act: -0.1700

Data Index: 578170 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 5.9236. Min Range: -5.9236

Max Act: 5.9236. Min Act: -0.1700

Data Index: 1188972 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 5.9236. Min Range: -5.9236

Max Act: 5.8924. Min Act: -0.1700

Data Index: 75967 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 5.9236. Min Range: -5.9236

Max Act: 5.7986. Min Act: -0.1700

Data Index: 880453 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 5.9236. Min Range: -5.9236

Max Act: 5.7986. Min Act: -0.1700

Data Index: 416899 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 5.9236. Min Range: -5.9236

Max Act: 5.7674. Min Act: -0.1700

Data Index: 558789 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 5.9236. Min Range: -5.9236

Max Act: 5.7986. Min Act: -0.1700

Data Index: 1145867 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 5.9236. Min Range: -5.9236

Max Act: 5.7674. Min Act: -0.1700

Data Index: 1133546 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 5.9236. Min Range: -5.9236

Max Act: 5.7674. Min Act: -0.1700

Data Index: 552551 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 5.9236. Min Range: -5.9236

Max Act: 5.7986. Min Act: -0.1700

Data Index: 615617 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 5.9236. Min Range: -5.9236

Max Act: 5.7674. Min Act: -0.1700

Data Index: 1048377 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 5.9236. Min Range: -5.9236

Max Act: 5.7049. Min Act: -0.1700

Data Index: 134148 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 5.9236. Min Range: -5.9236

Max Act: 5.7986. Min Act: -0.1700

Data Index: 909566 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 5.9236. Min Range: -5.9236

Max Act: 5.7361. Min Act: -0.1700

Data Index: 489304 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 5.9236. Min Range: -5.9236

Max Act: 5.7049. Min Act: -0.1700

Data Index: 536752 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 5.9236. Min Range: -5.9236

Max Act: 5.7049. Min Act: -0.1700

Data Index: 475260 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 5.9236. Min Range: -5.9236

Max Act: 5.7674. Min Act: -0.1700

Data Index: 264625 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 5.9236. Min Range: -5.9236

Max Act: 5.7361. Min Act: -0.1700

Data Index: 736049 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 5.9236. Min Range: -5.9236

Max Act: 5.6736. Min Act: -0.1700

Data Index: 230507 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 5.9236. Min Range: -5.9236

Max Act: 5.7361. Min Act: -0.1700

Data Index: 228291 (C4 (Web Text))

Max Activating Token Index: 596