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

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

Neuron 1806 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3835. Min Range: -3.3835

Max Act: 3.3678. Min Act: -0.1700

Data Index: 438775 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 3.3835. Min Range: -3.3835

Max Act: 3.3835. Min Act: -0.1700

Data Index: 987807 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 3.3835. Min Range: -3.3835

Max Act: 3.3521. Min Act: -0.1700

Data Index: 892771 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 3.3835. Min Range: -3.3835

Max Act: 3.2893. Min Act: -0.1700

Data Index: 402781 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 3.3835. Min Range: -3.3835

Max Act: 3.2736. Min Act: -0.1700

Data Index: 830616 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 3.3835. Min Range: -3.3835

Max Act: 3.2264. Min Act: -0.1700

Data Index: 975676 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 3.3835. Min Range: -3.3835

Max Act: 3.2579. Min Act: -0.1700

Data Index: 662586 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 3.3835. Min Range: -3.3835

Max Act: 3.2264. Min Act: -0.1700

Data Index: 599327 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 3.3835. Min Range: -3.3835

Max Act: 3.2264. Min Act: -0.1700

Data Index: 470447 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 3.3835. Min Range: -3.3835

Max Act: 3.2264. Min Act: -0.1700

Data Index: 330397 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 3.3835. Min Range: -3.3835

Max Act: 3.2422. Min Act: -0.1700

Data Index: 719432 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 3.3835. Min Range: -3.3835

Max Act: 3.2107. Min Act: -0.1700

Data Index: 417374 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 3.3835. Min Range: -3.3835

Max Act: 3.2107. Min Act: -0.1700

Data Index: 471531 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 3.3835. Min Range: -3.3835

Max Act: 3.1950. Min Act: -0.1700

Data Index: 1133794 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 3.3835. Min Range: -3.3835

Max Act: 3.1792. Min Act: -0.1700

Data Index: 815615 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 3.3835. Min Range: -3.3835

Max Act: 3.1635. Min Act: -0.1700

Data Index: 537697 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 3.3835. Min Range: -3.3835

Max Act: 3.1792. Min Act: -0.1700

Data Index: 23409 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 3.3835. Min Range: -3.3835

Max Act: 3.1162. Min Act: -0.1700

Data Index: 788215 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 3.3835. Min Range: -3.3835

Max Act: 3.1635. Min Act: -0.1700

Data Index: 930755 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 3.3835. Min Range: -3.3835

Max Act: 3.1320. Min Act: -0.1700

Data Index: 1154820 (C4 (Web Text))

Max Activating Token Index: 740