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

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

Neuron 709 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: 3.6870. Min Range: -3.6870

Max Act: 3.6557. Min Act: -0.1700

Data Index: 487162 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.6870. Min Act: -0.1700

Data Index: 521200 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.6870. Min Act: -0.1700

Data Index: 485033 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.5774. Min Act: -0.1700

Data Index: 1257473 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.5618. Min Act: -0.1700

Data Index: 544824 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.5931. Min Act: -0.1700

Data Index: 214916 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.5618. Min Act: -0.1700

Data Index: 33438 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.5461. Min Act: -0.1700

Data Index: 26801 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.5461. Min Act: -0.1700

Data Index: 462392 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.5305. Min Act: -0.1700

Data Index: 227246 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.4991. Min Act: -0.1700

Data Index: 172570 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.4834. Min Act: -0.1700

Data Index: 925377 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.4521. Min Act: -0.1700

Data Index: 212144 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.4991. Min Act: -0.1700

Data Index: 54842 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.4521. Min Act: -0.1700

Data Index: 681069 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.4991. Min Act: -0.1700

Data Index: 315286 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.4521. Min Act: -0.1700

Data Index: 594357 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.4834. Min Act: -0.1700

Data Index: 1212034 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.4521. Min Act: -0.1700

Data Index: 397884 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.4521. Min Act: -0.1700

Data Index: 260628 (C4 (Web Text))

Max Activating Token Index: 685