Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1798 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.3762. Min Act: -0.1700

Data Index: 1313278 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.3270. Min Act: -0.1699

Data Index: 1301105 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.3325. Min Act: -0.1700

Data Index: 394283 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.2867. Min Act: -0.1700

Data Index: 472941 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.2997. Min Act: -0.1700

Data Index: 264706 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.2569. Min Act: -0.1699

Data Index: 661365 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.2526. Min Act: -0.1700

Data Index: 699523 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.2400. Min Act: -0.1700

Data Index: 1155419 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.2356. Min Act: -0.1700

Data Index: 161946 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.2280. Min Act: -0.1700

Data Index: 82217 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.2087. Min Act: -0.1700

Data Index: 84159 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.1977. Min Act: -0.1700

Data Index: 401455 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.2022. Min Act: -0.1694

Data Index: 472732 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.1829. Min Act: -0.1699

Data Index: 237465 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.1928. Min Act: -0.1700

Data Index: 907276 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.1851. Min Act: -0.1687

Data Index: 131095 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.1840. Min Act: -0.1700

Data Index: 111173 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.1955. Min Act: -0.1699

Data Index: 1196028 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.1739. Min Act: -0.1700

Data Index: 912513 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.1595. Min Act: -0.1700

Data Index: 259396 (C4 (Web Text))

Max Activating Token Index: 657