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

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

Neuron 1253 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: 3.3564. Min Range: -3.3564

Max Act: 3.3564. Min Act: -0.1700

Data Index: 89532 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 3.3564. Min Range: -3.3564

Max Act: 3.2778. Min Act: -0.1700

Data Index: 963432 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 3.3564. Min Range: -3.3564

Max Act: 3.2621. Min Act: -0.1700

Data Index: 35341 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 3.3564. Min Range: -3.3564

Max Act: 3.2464. Min Act: -0.1700

Data Index: 1010585 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 3.3564. Min Range: -3.3564

Max Act: 3.2150. Min Act: -0.1700

Data Index: 1180769 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 3.3564. Min Range: -3.3564

Max Act: 3.2307. Min Act: -0.1700

Data Index: 409698 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 3.3564. Min Range: -3.3564

Max Act: 3.2150. Min Act: -0.1700

Data Index: 1172045 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 3.3564. Min Range: -3.3564

Max Act: 3.2150. Min Act: -0.1700

Data Index: 1309442 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 3.3564. Min Range: -3.3564

Max Act: 3.1520. Min Act: -0.1700

Data Index: 256314 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 3.3564. Min Range: -3.3564

Max Act: 3.1992. Min Act: -0.1700

Data Index: 943641 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 3.3564. Min Range: -3.3564

Max Act: 3.1992. Min Act: -0.1700

Data Index: 483350 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 3.3564. Min Range: -3.3564

Max Act: 3.1835. Min Act: -0.1700

Data Index: 1102167 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 3.3564. Min Range: -3.3564

Max Act: 3.1520. Min Act: -0.1700

Data Index: 961677 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 3.3564. Min Range: -3.3564

Max Act: 3.1835. Min Act: -0.1700

Data Index: 1211130 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 3.3564. Min Range: -3.3564

Max Act: 3.1835. Min Act: -0.1700

Data Index: 1030399 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 3.3564. Min Range: -3.3564

Max Act: 3.1363. Min Act: -0.1700

Data Index: 598996 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 3.3564. Min Range: -3.3564

Max Act: 3.1520. Min Act: -0.1700

Data Index: 836370 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 3.3564. Min Range: -3.3564

Max Act: 3.1363. Min Act: -0.1700

Data Index: 445063 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 3.3564. Min Range: -3.3564

Max Act: 3.1047. Min Act: -0.1700

Data Index: 1122000 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 3.3564. Min Range: -3.3564

Max Act: 3.1520. Min Act: -0.1700

Data Index: 253088 (C4 (Web Text))

Max Activating Token Index: 586