Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1298 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.3680. Min Range: -4.3680

Max Act: 4.3680. Min Act: -0.1700

Data Index: 969124 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 4.3680. Min Range: -4.3680

Max Act: 4.2730. Min Act: -0.1700

Data Index: 1291933 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 4.3680. Min Range: -4.3680

Max Act: 4.2686. Min Act: -0.1700

Data Index: 915051 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 4.3680. Min Range: -4.3680

Max Act: 4.2381. Min Act: -0.1700

Data Index: 51716 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 4.3680. Min Range: -4.3680

Max Act: 4.2376. Min Act: -0.1700

Data Index: 971710 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 4.3680. Min Range: -4.3680

Max Act: 4.2084. Min Act: -0.1700

Data Index: 23826 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 4.3680. Min Range: -4.3680

Max Act: 4.2015. Min Act: -0.1700

Data Index: 1026182 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 4.3680. Min Range: -4.3680

Max Act: 4.2061. Min Act: -0.1700

Data Index: 1118259 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 4.3680. Min Range: -4.3680

Max Act: 4.1829. Min Act: -0.1700

Data Index: 506837 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 4.3680. Min Range: -4.3680

Max Act: 4.1988. Min Act: -0.1700

Data Index: 1234511 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 4.3680. Min Range: -4.3680

Max Act: 4.1536. Min Act: -0.1700

Data Index: 924526 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 4.3680. Min Range: -4.3680

Max Act: 4.1723. Min Act: -0.1700

Data Index: 202758 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 4.3680. Min Range: -4.3680

Max Act: 4.1573. Min Act: -0.1700

Data Index: 504685 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 4.3680. Min Range: -4.3680

Max Act: 4.1674. Min Act: -0.0866

Data Index: 1146867 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 4.3680. Min Range: -4.3680

Max Act: 4.1634. Min Act: -0.1700

Data Index: 1227202 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 4.3680. Min Range: -4.3680

Max Act: 4.1764. Min Act: -0.1700

Data Index: 469899 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 4.3680. Min Range: -4.3680

Max Act: 4.1074. Min Act: -0.1700

Data Index: 910014 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 4.3680. Min Range: -4.3680

Max Act: 4.1282. Min Act: -0.1700

Data Index: 630565 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 4.3680. Min Range: -4.3680

Max Act: 4.0980. Min Act: -0.1700

Data Index: 545122 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 4.3680. Min Range: -4.3680

Max Act: 4.1070. Min Act: -0.1440

Data Index: 548886 (C4 (Web Text))

Max Activating Token Index: 360