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

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

Neuron 928 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: 5.2538. Min Range: -5.2538

Max Act: 5.2538. Min Act: -0.1700

Data Index: 996332 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 5.2538. Min Range: -5.2538

Max Act: 5.2538. Min Act: -0.1700

Data Index: 1288261 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 5.2538. Min Range: -5.2538

Max Act: 5.1601. Min Act: -0.1700

Data Index: 1311562 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 5.2538. Min Range: -5.2538

Max Act: 5.1913. Min Act: -0.1700

Data Index: 462235 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 5.2538. Min Range: -5.2538

Max Act: 5.1288. Min Act: -0.1700

Data Index: 468766 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 5.2538. Min Range: -5.2538

Max Act: 5.0976. Min Act: -0.1700

Data Index: 904397 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 5.2538. Min Range: -5.2538

Max Act: 5.0976. Min Act: -0.1700

Data Index: 812099 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 5.2538. Min Range: -5.2538

Max Act: 5.0663. Min Act: -0.1700

Data Index: 100913 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 5.2538. Min Range: -5.2538

Max Act: 5.0663. Min Act: -0.1700

Data Index: 409438 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 5.2538. Min Range: -5.2538

Max Act: 5.0663. Min Act: -0.1700

Data Index: 1150273 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 5.2538. Min Range: -5.2538

Max Act: 5.0663. Min Act: -0.1700

Data Index: 691206 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 5.2538. Min Range: -5.2538

Max Act: 5.0038. Min Act: -0.1700

Data Index: 850423 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 5.2538. Min Range: -5.2538

Max Act: 4.9726. Min Act: -0.1700

Data Index: 594034 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 5.2538. Min Range: -5.2538

Max Act: 5.0038. Min Act: -0.1700

Data Index: 188880 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 5.2538. Min Range: -5.2538

Max Act: 4.9726. Min Act: -0.1700

Data Index: 1281265 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 5.2538. Min Range: -5.2538

Max Act: 4.9413. Min Act: -0.1700

Data Index: 611819 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 5.2538. Min Range: -5.2538

Max Act: 4.9413. Min Act: -0.1700

Data Index: 43585 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 5.2538. Min Range: -5.2538

Max Act: 4.9726. Min Act: -0.1700

Data Index: 13585 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 5.2538. Min Range: -5.2538

Max Act: 4.9726. Min Act: -0.1700

Data Index: 455118 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 5.2538. Min Range: -5.2538

Max Act: 4.9413. Min Act: -0.1700

Data Index: 1256809 (C4 (Web Text))

Max Activating Token Index: 950