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

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

Neuron 2005 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.9639. Min Act: -0.1700

Data Index: 272771 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.9639. Min Act: -0.1700

Data Index: 31387 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.9483. Min Act: -0.1700

Data Index: 257191 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.8858. Min Act: -0.1700

Data Index: 1249852 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.9483. Min Act: -0.1700

Data Index: 1078438 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.8858. Min Act: -0.1700

Data Index: 1124435 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.8232. Min Act: -0.1700

Data Index: 870139 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.7919. Min Act: -0.1700

Data Index: 252270 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.8545. Min Act: -0.1700

Data Index: 1303307 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.7450. Min Act: -0.1700

Data Index: 796311 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.7919. Min Act: -0.1700

Data Index: 489027 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.7763. Min Act: -0.1700

Data Index: 37240 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.7919. Min Act: -0.1700

Data Index: 962027 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.7606. Min Act: -0.1700

Data Index: 1171749 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.7450. Min Act: -0.1700

Data Index: 86213 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.7763. Min Act: -0.1700

Data Index: 384274 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.6668. Min Act: -0.1700

Data Index: 997238 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.7450. Min Act: -0.1700

Data Index: 71277 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.7294. Min Act: -0.1700

Data Index: 1015598 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 3.9639. Min Range: -3.9639

Max Act: 3.7137. Min Act: -0.1700

Data Index: 491514 (C4 (Web Text))

Max Activating Token Index: 480