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

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

Neuron 1145 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1445. Min Range: -4.1445

Max Act: 4.0820. Min Act: -0.1700

Data Index: 421938 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 4.1445. Min Range: -4.1445

Max Act: 4.1445. Min Act: -0.1700

Data Index: 658555 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 4.1445. Min Range: -4.1445

Max Act: 4.0820. Min Act: -0.1700

Data Index: 460486 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 4.1445. Min Range: -4.1445

Max Act: 4.0507. Min Act: -0.1700

Data Index: 145285 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 4.1445. Min Range: -4.1445

Max Act: 4.0195. Min Act: -0.1700

Data Index: 8387 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 4.1445. Min Range: -4.1445

Max Act: 4.0507. Min Act: -0.1700

Data Index: 120745 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 4.1445. Min Range: -4.1445

Max Act: 3.9570. Min Act: -0.1700

Data Index: 369053 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 4.1445. Min Range: -4.1445

Max Act: 3.9570. Min Act: -0.1700

Data Index: 219385 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 4.1445. Min Range: -4.1445

Max Act: 3.9882. Min Act: -0.1700

Data Index: 1188484 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 4.1445. Min Range: -4.1445

Max Act: 3.8944. Min Act: -0.1700

Data Index: 168683 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 4.1445. Min Range: -4.1445

Max Act: 3.9257. Min Act: -0.1700

Data Index: 1299455 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 4.1445. Min Range: -4.1445

Max Act: 3.9257. Min Act: -0.1700

Data Index: 198113 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 4.1445. Min Range: -4.1445

Max Act: 3.8944. Min Act: -0.1700

Data Index: 262717 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 4.1445. Min Range: -4.1445

Max Act: 3.9257. Min Act: -0.1700

Data Index: 440419 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 4.1445. Min Range: -4.1445

Max Act: 3.8944. Min Act: -0.1700

Data Index: 183205 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 4.1445. Min Range: -4.1445

Max Act: 3.8944. Min Act: -0.1700

Data Index: 199810 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 4.1445. Min Range: -4.1445

Max Act: 3.8944. Min Act: -0.1700

Data Index: 852784 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 4.1445. Min Range: -4.1445

Max Act: 3.8631. Min Act: -0.1700

Data Index: 752674 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 4.1445. Min Range: -4.1445

Max Act: 3.8944. Min Act: -0.1700

Data Index: 67888 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 4.1445. Min Range: -4.1445

Max Act: 3.8944. Min Act: -0.1700

Data Index: 756695 (C4 (Web Text))

Max Activating Token Index: 557