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

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

Neuron 1975 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: 3.1335. Min Range: -3.1335

Max Act: 3.1335. Min Act: -0.1700

Data Index: 1078665 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 3.1335. Min Range: -3.1335

Max Act: 3.1177. Min Act: -0.1700

Data Index: 1016272 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 3.1335. Min Range: -3.1335

Max Act: 3.1020. Min Act: -0.1700

Data Index: 559814 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 3.1335. Min Range: -3.1335

Max Act: 3.1020. Min Act: -0.1700

Data Index: 1350177 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 3.1335. Min Range: -3.1335

Max Act: 3.0862. Min Act: -0.1700

Data Index: 128333 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 3.1335. Min Range: -3.1335

Max Act: 3.0862. Min Act: -0.1700

Data Index: 87905 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 3.1335. Min Range: -3.1335

Max Act: 3.1020. Min Act: -0.1700

Data Index: 999303 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 3.1335. Min Range: -3.1335

Max Act: 3.0704. Min Act: -0.1700

Data Index: 1204320 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 3.1335. Min Range: -3.1335

Max Act: 3.0862. Min Act: -0.1700

Data Index: 237489 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 3.1335. Min Range: -3.1335

Max Act: 3.0704. Min Act: -0.1700

Data Index: 735276 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 3.1335. Min Range: -3.1335

Max Act: 3.0704. Min Act: -0.1700

Data Index: 983741 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 3.1335. Min Range: -3.1335

Max Act: 3.0704. Min Act: -0.1700

Data Index: 679436 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 3.1335. Min Range: -3.1335

Max Act: 3.0547. Min Act: -0.1700

Data Index: 747547 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 3.1335. Min Range: -3.1335

Max Act: 3.0704. Min Act: -0.1700

Data Index: 797595 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 3.1335. Min Range: -3.1335

Max Act: 3.0547. Min Act: -0.1700

Data Index: 695759 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 3.1335. Min Range: -3.1335

Max Act: 3.0547. Min Act: -0.1700

Data Index: 76531 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 3.1335. Min Range: -3.1335

Max Act: 3.0389. Min Act: -0.1700

Data Index: 209259 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 3.1335. Min Range: -3.1335

Max Act: 3.0547. Min Act: -0.1700

Data Index: 1122547 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 3.1335. Min Range: -3.1335

Max Act: 3.0704. Min Act: -0.1700

Data Index: 1222655 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 3.1335. Min Range: -3.1335

Max Act: 3.0389. Min Act: -0.1700

Data Index: 1115937 (C4 (Web Text))

Max Activating Token Index: 925