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

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

Neuron 1720 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6280. Min Range: -3.6280

Max Act: 3.6124. Min Act: -0.1700

Data Index: 420793 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 3.6280. Min Range: -3.6280

Max Act: 3.6124. Min Act: -0.1700

Data Index: 372404 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 3.6280. Min Range: -3.6280

Max Act: 3.6280. Min Act: -0.1700

Data Index: 575947 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 3.6280. Min Range: -3.6280

Max Act: 3.6124. Min Act: -0.1700

Data Index: 882171 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 3.6280. Min Range: -3.6280

Max Act: 3.5967. Min Act: -0.1700

Data Index: 764062 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 3.6280. Min Range: -3.6280

Max Act: 3.5810. Min Act: -0.1700

Data Index: 1003067 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 3.6280. Min Range: -3.6280

Max Act: 3.5497. Min Act: -0.1700

Data Index: 900143 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 3.6280. Min Range: -3.6280

Max Act: 3.5654. Min Act: -0.1700

Data Index: 1149285 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 3.6280. Min Range: -3.6280

Max Act: 3.5341. Min Act: -0.1700

Data Index: 84734 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 3.6280. Min Range: -3.6280

Max Act: 3.5184. Min Act: -0.1700

Data Index: 365209 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 3.6280. Min Range: -3.6280

Max Act: 3.5184. Min Act: -0.1700

Data Index: 805557 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 3.6280. Min Range: -3.6280

Max Act: 3.5027. Min Act: -0.1700

Data Index: 932462 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 3.6280. Min Range: -3.6280

Max Act: 3.5184. Min Act: -0.1700

Data Index: 1243157 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 3.6280. Min Range: -3.6280

Max Act: 3.5027. Min Act: -0.1700

Data Index: 572768 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 3.6280. Min Range: -3.6280

Max Act: 3.4714. Min Act: -0.1700

Data Index: 620271 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 3.6280. Min Range: -3.6280

Max Act: 3.4871. Min Act: -0.1700

Data Index: 112809 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 3.6280. Min Range: -3.6280

Max Act: 3.4871. Min Act: -0.1700

Data Index: 215689 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 3.6280. Min Range: -3.6280

Max Act: 3.4714. Min Act: -0.1700

Data Index: 1285140 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 3.6280. Min Range: -3.6280

Max Act: 3.4557. Min Act: -0.1700

Data Index: 997012 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 3.6280. Min Range: -3.6280

Max Act: 3.4714. Min Act: -0.1700

Data Index: 675939 (C4 (Web Text))

Max Activating Token Index: 644