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

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

Neuron 380 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3120. Min Range: -3.3120

Max Act: 3.2806. Min Act: -0.1700

Data Index: 879670 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 3.3120. Min Range: -3.3120

Max Act: 3.2963. Min Act: -0.1700

Data Index: 90268 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 3.3120. Min Range: -3.3120

Max Act: 3.3120. Min Act: -0.1700

Data Index: 364167 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 3.3120. Min Range: -3.3120

Max Act: 3.2963. Min Act: -0.1700

Data Index: 1071073 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 3.3120. Min Range: -3.3120

Max Act: 3.2963. Min Act: -0.1700

Data Index: 837357 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 3.3120. Min Range: -3.3120

Max Act: 3.2806. Min Act: -0.1700

Data Index: 129118 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 3.3120. Min Range: -3.3120

Max Act: 3.2648. Min Act: -0.1700

Data Index: 62742 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 3.3120. Min Range: -3.3120

Max Act: 3.2806. Min Act: -0.1700

Data Index: 984712 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 3.3120. Min Range: -3.3120

Max Act: 3.2806. Min Act: -0.1700

Data Index: 1192484 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 3.3120. Min Range: -3.3120

Max Act: 3.2963. Min Act: -0.1700

Data Index: 417989 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 3.3120. Min Range: -3.3120

Max Act: 3.2806. Min Act: -0.1700

Data Index: 1284935 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 3.3120. Min Range: -3.3120

Max Act: 3.2806. Min Act: -0.1700

Data Index: 1301122 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 3.3120. Min Range: -3.3120

Max Act: 3.2963. Min Act: -0.1700

Data Index: 552170 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 3.3120. Min Range: -3.3120

Max Act: 3.2806. Min Act: -0.1700

Data Index: 765727 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 3.3120. Min Range: -3.3120

Max Act: 3.2648. Min Act: -0.1700

Data Index: 549991 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 3.3120. Min Range: -3.3120

Max Act: 3.2491. Min Act: -0.1700

Data Index: 593457 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 3.3120. Min Range: -3.3120

Max Act: 3.2491. Min Act: -0.1700

Data Index: 632098 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 3.3120. Min Range: -3.3120

Max Act: 3.2648. Min Act: -0.1700

Data Index: 122202 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 3.3120. Min Range: -3.3120

Max Act: 3.2648. Min Act: -0.1700

Data Index: 688854 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 3.3120. Min Range: -3.3120

Max Act: 3.2648. Min Act: -0.1700

Data Index: 65846 (C4 (Web Text))

Max Activating Token Index: 226