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

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

Neuron 1590 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: 4.3359. Min Range: -4.3359

Max Act: 4.3359. Min Act: -0.1700

Data Index: 575621 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 4.3359. Min Range: -4.3359

Max Act: 4.2507. Min Act: -0.1700

Data Index: 1048935 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 4.3359. Min Range: -4.3359

Max Act: 4.1883. Min Act: -0.1700

Data Index: 1226112 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 4.3359. Min Range: -4.3359

Max Act: 4.1851. Min Act: -0.1700

Data Index: 1014698 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 4.3359. Min Range: -4.3359

Max Act: 4.1918. Min Act: -0.1700

Data Index: 918643 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 4.3359. Min Range: -4.3359

Max Act: 4.1832. Min Act: -0.1700

Data Index: 1166217 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 4.3359. Min Range: -4.3359

Max Act: 4.1597. Min Act: -0.1700

Data Index: 1088932 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 4.3359. Min Range: -4.3359

Max Act: 4.1455. Min Act: -0.1700

Data Index: 794568 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 4.3359. Min Range: -4.3359

Max Act: 4.1142. Min Act: -0.1700

Data Index: 898356 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 4.3359. Min Range: -4.3359

Max Act: 4.1320. Min Act: -0.1700

Data Index: 715087 (C4 (Web Text))

Max Activating Token Index: 391

Text #10

Max Range: 4.3359. Min Range: -4.3359

Max Act: 4.1214. Min Act: -0.1700

Data Index: 1343128 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 4.3359. Min Range: -4.3359

Max Act: 4.1487. Min Act: -0.1700

Data Index: 993531 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 4.3359. Min Range: -4.3359

Max Act: 4.1104. Min Act: -0.1700

Data Index: 560807 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 4.3359. Min Range: -4.3359

Max Act: 4.1129. Min Act: -0.1700

Data Index: 1326099 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 4.3359. Min Range: -4.3359

Max Act: 4.1058. Min Act: -0.1700

Data Index: 676653 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 4.3359. Min Range: -4.3359

Max Act: 4.0984. Min Act: -0.1700

Data Index: 783037 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 4.3359. Min Range: -4.3359

Max Act: 4.1008. Min Act: -0.1700

Data Index: 349279 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 4.3359. Min Range: -4.3359

Max Act: 4.0702. Min Act: -0.1700

Data Index: 949085 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 4.3359. Min Range: -4.3359

Max Act: 4.0711. Min Act: -0.1700

Data Index: 1235190 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 4.3359. Min Range: -4.3359

Max Act: 4.1106. Min Act: -0.1700

Data Index: 100461 (C4 (Web Text))

Max Activating Token Index: 649