Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1675 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6581. Min Range: -3.6581

Max Act: 3.6581. Min Act: -0.1700

Data Index: 1156687 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 3.6581. Min Range: -3.6581

Max Act: 3.6268. Min Act: -0.1700

Data Index: 126878 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 3.6581. Min Range: -3.6581

Max Act: 3.5642. Min Act: -0.1700

Data Index: 785369 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 3.6581. Min Range: -3.6581

Max Act: 3.5642. Min Act: -0.1700

Data Index: 748735 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 3.6581. Min Range: -3.6581

Max Act: 3.5642. Min Act: -0.1700

Data Index: 926385 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 3.6581. Min Range: -3.6581

Max Act: 3.5642. Min Act: -0.1700

Data Index: 56804 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 3.6581. Min Range: -3.6581

Max Act: 3.5642. Min Act: -0.1700

Data Index: 249114 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 3.6581. Min Range: -3.6581

Max Act: 3.5172. Min Act: -0.1700

Data Index: 990109 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 3.6581. Min Range: -3.6581

Max Act: 3.5015. Min Act: -0.1700

Data Index: 1150470 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 3.6581. Min Range: -3.6581

Max Act: 3.4074. Min Act: -0.1700

Data Index: 799847 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 3.6581. Min Range: -3.6581

Max Act: 3.4388. Min Act: -0.1700

Data Index: 1060251 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 3.6581. Min Range: -3.6581

Max Act: 3.4074. Min Act: -0.1700

Data Index: 1215063 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 3.6581. Min Range: -3.6581

Max Act: 3.3761. Min Act: -0.1700

Data Index: 664835 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 3.6581. Min Range: -3.6581

Max Act: 3.3447. Min Act: -0.1700

Data Index: 1314300 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 3.6581. Min Range: -3.6581

Max Act: 3.3604. Min Act: -0.1700

Data Index: 1325361 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 3.6581. Min Range: -3.6581

Max Act: 3.3447. Min Act: -0.1700

Data Index: 1284566 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 3.6581. Min Range: -3.6581

Max Act: 3.3447. Min Act: -0.1700

Data Index: 1008455 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 3.6581. Min Range: -3.6581

Max Act: 3.3447. Min Act: -0.1700

Data Index: 77948 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 3.6581. Min Range: -3.6581

Max Act: 3.3290. Min Act: -0.1700

Data Index: 808920 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 3.6581. Min Range: -3.6581

Max Act: 3.3290. Min Act: -0.1700

Data Index: 717984 (C4 (Web Text))

Max Activating Token Index: 986