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

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

Neuron 1100 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: 3.6666. Min Range: -3.6666

Max Act: 3.6666. Min Act: -0.1700

Data Index: 486797 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.5727. Min Act: -0.1700

Data Index: 40259 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.5727. Min Act: -0.1700

Data Index: 426282 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.5414. Min Act: -0.1700

Data Index: 169567 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.5727. Min Act: -0.1700

Data Index: 1104322 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.5727. Min Act: -0.1700

Data Index: 919830 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.4787. Min Act: -0.1700

Data Index: 517625 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.5727. Min Act: -0.1700

Data Index: 943541 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.5727. Min Act: -0.1700

Data Index: 323503 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.5100. Min Act: -0.1700

Data Index: 846316 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.5257. Min Act: -0.1700

Data Index: 585018 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.4944. Min Act: -0.1700

Data Index: 504476 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.5100. Min Act: -0.1700

Data Index: 276651 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.5100. Min Act: -0.1700

Data Index: 1320624 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.5100. Min Act: -0.1700

Data Index: 394551 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.5100. Min Act: -0.1700

Data Index: 14269 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.5727. Min Act: -0.1700

Data Index: 18872 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.5570. Min Act: -0.1700

Data Index: 790795 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.5414. Min Act: -0.1700

Data Index: 1279875 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 3.6666. Min Range: -3.6666

Max Act: 3.4787. Min Act: -0.1700

Data Index: 600646 (C4 (Web Text))

Max Activating Token Index: 276