Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1099 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.0705. Min Range: -3.0705

Max Act: 3.0705. Min Act: -0.1700

Data Index: 321851 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 3.0705. Min Range: -3.0705

Max Act: 3.0512. Min Act: -0.1700

Data Index: 680117 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 3.0705. Min Range: -3.0705

Max Act: 3.0297. Min Act: -0.1700

Data Index: 1126466 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.9971. Min Act: -0.1700

Data Index: 970734 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.9310. Min Act: -0.1700

Data Index: 1547392 (Python Code)

Max Activating Token Index: 911

Text #5

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.9659. Min Act: -0.1700

Data Index: 936730 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.9516. Min Act: -0.1700

Data Index: 722420 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.9164. Min Act: -0.1700

Data Index: 280241 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.9493. Min Act: -0.1700

Data Index: 1516954 (Python Code)

Max Activating Token Index: 583

Text #9

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.9267. Min Act: -0.1700

Data Index: 1506366 (Python Code)

Max Activating Token Index: 306

Text #10

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.9557. Min Act: -0.1700

Data Index: 970863 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.9042. Min Act: -0.1700

Data Index: 124021 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.9062. Min Act: -0.1700

Data Index: 1200328 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.8968. Min Act: -0.1700

Data Index: 1575096 (Python Code)

Max Activating Token Index: 377

Text #14

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.8497. Min Act: -0.1700

Data Index: 1267170 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.8472. Min Act: -0.1700

Data Index: 592458 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.8434. Min Act: -0.1700

Data Index: 318031 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.8435. Min Act: -0.1700

Data Index: 9467 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.8139. Min Act: -0.1700

Data Index: 34184 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 3.0705. Min Range: -3.0705

Max Act: 2.8653. Min Act: -0.1700

Data Index: 1485708 (Python Code)

Max Activating Token Index: 959