Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 909 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3560. Min Range: -3.3560

Max Act: 3.3560. Min Act: -0.1700

Data Index: 1373475 (Python Code)

Max Activating Token Index: 289

Text #1

Max Range: 3.3560. Min Range: -3.3560

Max Act: 3.1831. Min Act: -0.1700

Data Index: 1376687 (Python Code)

Max Activating Token Index: 547

Text #2

Max Range: 3.3560. Min Range: -3.3560

Max Act: 3.1359. Min Act: -0.1700

Data Index: 1488216 (Python Code)

Max Activating Token Index: 228

Text #3

Max Range: 3.3560. Min Range: -3.3560

Max Act: 3.1359. Min Act: -0.1700

Data Index: 453705 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 3.3560. Min Range: -3.3560

Max Act: 3.1044. Min Act: -0.1700

Data Index: 307495 (C4 (Web Text))

Max Activating Token Index: 1015

Text #5

Max Range: 3.3560. Min Range: -3.3560

Max Act: 3.0412. Min Act: -0.1700

Data Index: 1102023 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 3.3560. Min Range: -3.3560

Max Act: 3.0254. Min Act: -0.1700

Data Index: 1135316 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 3.3560. Min Range: -3.3560

Max Act: 2.9938. Min Act: -0.1700

Data Index: 858785 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 3.3560. Min Range: -3.3560

Max Act: 2.9622. Min Act: -0.1700

Data Index: 715759 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 3.3560. Min Range: -3.3560

Max Act: 2.9464. Min Act: -0.1700

Data Index: 512191 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 3.3560. Min Range: -3.3560

Max Act: 2.9305. Min Act: -0.1700

Data Index: 454257 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 3.3560. Min Range: -3.3560

Max Act: 2.9147. Min Act: -0.1700

Data Index: 1635324 (Python Code)

Max Activating Token Index: 582

Text #12

Max Range: 3.3560. Min Range: -3.3560

Max Act: 2.8988. Min Act: -0.1700

Data Index: 773375 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 3.3560. Min Range: -3.3560

Max Act: 2.8671. Min Act: -0.1700

Data Index: 223539 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 3.3560. Min Range: -3.3560

Max Act: 2.8671. Min Act: -0.1700

Data Index: 722891 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 3.3560. Min Range: -3.3560

Max Act: 2.8671. Min Act: -0.1700

Data Index: 1235034 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 3.3560. Min Range: -3.3560

Max Act: 2.8671. Min Act: -0.1700

Data Index: 1022604 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 3.3560. Min Range: -3.3560

Max Act: 2.8512. Min Act: -0.1700

Data Index: 698651 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 3.3560. Min Range: -3.3560

Max Act: 2.8512. Min Act: -0.1700

Data Index: 1337852 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 3.3560. Min Range: -3.3560

Max Act: 2.8512. Min Act: -0.1700

Data Index: 1253161 (C4 (Web Text))

Max Activating Token Index: 307