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

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

Neuron 1520 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: 4.2106. Min Range: -4.2106

Max Act: 4.2106. Min Act: -0.1694

Data Index: 1344811 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 4.2106. Min Range: -4.2106

Max Act: 4.1033. Min Act: -0.1634

Data Index: 168799 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 4.2106. Min Range: -4.2106

Max Act: 4.0221. Min Act: -0.1700

Data Index: 1234250 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 4.2106. Min Range: -4.2106

Max Act: 3.9536. Min Act: -0.1693

Data Index: 1642500 (Python Code)

Max Activating Token Index: 898

Text #4

Max Range: 4.2106. Min Range: -4.2106

Max Act: 3.9280. Min Act: -0.1700

Data Index: 251478 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 4.2106. Min Range: -4.2106

Max Act: 3.9320. Min Act: -0.1699

Data Index: 819952 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 4.2106. Min Range: -4.2106

Max Act: 3.9183. Min Act: -0.1698

Data Index: 1111518 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 4.2106. Min Range: -4.2106

Max Act: 3.8723. Min Act: -0.1699

Data Index: 96388 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 4.2106. Min Range: -4.2106

Max Act: 3.8424. Min Act: -0.1676

Data Index: 430937 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 4.2106. Min Range: -4.2106

Max Act: 3.8450. Min Act: -0.1700

Data Index: 250485 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 4.2106. Min Range: -4.2106

Max Act: 3.8358. Min Act: -0.1698

Data Index: 864432 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 4.2106. Min Range: -4.2106

Max Act: 3.8267. Min Act: -0.1700

Data Index: 956120 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 4.2106. Min Range: -4.2106

Max Act: 3.8072. Min Act: -0.1700

Data Index: 509364 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 4.2106. Min Range: -4.2106

Max Act: 3.8028. Min Act: -0.1696

Data Index: 250269 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 4.2106. Min Range: -4.2106

Max Act: 3.8014. Min Act: -0.1681

Data Index: 106298 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 4.2106. Min Range: -4.2106

Max Act: 3.7747. Min Act: -0.1700

Data Index: 613259 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 4.2106. Min Range: -4.2106

Max Act: 3.8005. Min Act: -0.1699

Data Index: 820303 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 4.2106. Min Range: -4.2106

Max Act: 3.7891. Min Act: -0.1699

Data Index: 882412 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 4.2106. Min Range: -4.2106

Max Act: 3.7968. Min Act: -0.1700

Data Index: 976765 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 4.2106. Min Range: -4.2106

Max Act: 3.7788. Min Act: -0.1696

Data Index: 572538 (C4 (Web Text))

Max Activating Token Index: 360