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

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

Neuron 1680 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3403. Min Range: -3.3403

Max Act: 3.3403. Min Act: -0.1700

Data Index: 1652484 (Python Code)

Max Activating Token Index: 1004

Text #1

Max Range: 3.3403. Min Range: -3.3403

Max Act: 3.3246. Min Act: -0.1700

Data Index: 1189788 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 3.3403. Min Range: -3.3403

Max Act: 3.3403. Min Act: -0.1700

Data Index: 542352 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 3.3403. Min Range: -3.3403

Max Act: 3.3246. Min Act: -0.1700

Data Index: 717361 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 3.3403. Min Range: -3.3403

Max Act: 3.2618. Min Act: -0.1700

Data Index: 587657 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 3.3403. Min Range: -3.3403

Max Act: 3.3246. Min Act: -0.1700

Data Index: 1298272 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 3.3403. Min Range: -3.3403

Max Act: 3.2775. Min Act: -0.1700

Data Index: 364271 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 3.3403. Min Range: -3.3403

Max Act: 3.2775. Min Act: -0.1700

Data Index: 877141 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 3.3403. Min Range: -3.3403

Max Act: 3.2932. Min Act: -0.1700

Data Index: 199813 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 3.3403. Min Range: -3.3403

Max Act: 3.2304. Min Act: -0.1700

Data Index: 761232 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 3.3403. Min Range: -3.3403

Max Act: 3.2461. Min Act: -0.1700

Data Index: 1304932 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 3.3403. Min Range: -3.3403

Max Act: 3.2461. Min Act: -0.1700

Data Index: 809126 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 3.3403. Min Range: -3.3403

Max Act: 3.2618. Min Act: -0.1700

Data Index: 1621111 (Python Code)

Max Activating Token Index: 648

Text #13

Max Range: 3.3403. Min Range: -3.3403

Max Act: 3.1832. Min Act: -0.1700

Data Index: 443237 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 3.3403. Min Range: -3.3403

Max Act: 3.2147. Min Act: -0.1700

Data Index: 509520 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 3.3403. Min Range: -3.3403

Max Act: 3.2304. Min Act: -0.1700

Data Index: 1180121 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 3.3403. Min Range: -3.3403

Max Act: 3.2304. Min Act: -0.1700

Data Index: 1237740 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 3.3403. Min Range: -3.3403

Max Act: 3.2304. Min Act: -0.1700

Data Index: 1069109 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 3.3403. Min Range: -3.3403

Max Act: 3.2147. Min Act: -0.1700

Data Index: 531894 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 3.3403. Min Range: -3.3403

Max Act: 3.1989. Min Act: -0.1700

Data Index: 1069989 (C4 (Web Text))

Max Activating Token Index: 692