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

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

Neuron 1693 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.6475. Min Act: -0.1700

Data Index: 1047376 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.6162. Min Act: -0.1700

Data Index: 949029 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.5849. Min Act: -0.1700

Data Index: 1328790 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.6005. Min Act: -0.1700

Data Index: 1030478 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.5849. Min Act: -0.1700

Data Index: 904224 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.5379. Min Act: -0.1700

Data Index: 812497 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.5222. Min Act: -0.1700

Data Index: 326081 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.5065. Min Act: -0.1700

Data Index: 1103623 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.4752. Min Act: -0.1700

Data Index: 452631 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.5065. Min Act: -0.1700

Data Index: 1149541 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.4439. Min Act: -0.1700

Data Index: 514431 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.4595. Min Act: -0.1700

Data Index: 698943 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.3340. Min Act: -0.1700

Data Index: 1279933 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.3497. Min Act: -0.1700

Data Index: 885415 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.3026. Min Act: -0.1700

Data Index: 1025239 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.2555. Min Act: -0.1700

Data Index: 406463 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.2398. Min Act: -0.1700

Data Index: 185259 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.2712. Min Act: -0.1700

Data Index: 1140128 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.2555. Min Act: -0.1700

Data Index: 353564 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.2555. Min Act: -0.1700

Data Index: 1329892 (C4 (Web Text))

Max Activating Token Index: 197