Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1034 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.2523. Min Act: -0.1700

Data Index: 323420 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.1421. Min Act: -0.1700

Data Index: 1082731 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.1264. Min Act: -0.1700

Data Index: 875101 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.1264. Min Act: -0.1700

Data Index: 139081 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.0475. Min Act: -0.1700

Data Index: 547057 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.0633. Min Act: -0.1700

Data Index: 470389 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.0475. Min Act: -0.1700

Data Index: 553402 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.0475. Min Act: -0.1700

Data Index: 687020 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.9843. Min Act: -0.1700

Data Index: 885776 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.9685. Min Act: -0.1700

Data Index: 802269 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.0001. Min Act: -0.1700

Data Index: 578929 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.0317. Min Act: -0.1700

Data Index: 1124757 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.0001. Min Act: -0.1700

Data Index: 1188771 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.9843. Min Act: -0.1700

Data Index: 700115 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.0001. Min Act: -0.1700

Data Index: 981766 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.9843. Min Act: -0.1700

Data Index: 423543 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.9843. Min Act: -0.1700

Data Index: 1257202 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.9843. Min Act: -0.1700

Data Index: 700222 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.9527. Min Act: -0.1700

Data Index: 505854 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.9685. Min Act: -0.1700

Data Index: 675298 (C4 (Web Text))

Max Activating Token Index: 217