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

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

Neuron 1034 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: 2.8748. Min Range: -2.8748

Max Act: 2.8748. Min Act: -0.1698

Data Index: 1072184 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 2.8748. Min Range: -2.8748

Max Act: 2.8389. Min Act: -0.1700

Data Index: 992010 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 2.8748. Min Range: -2.8748

Max Act: 2.8159. Min Act: -0.1700

Data Index: 596430 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 2.8748. Min Range: -2.8748

Max Act: 2.8125. Min Act: -0.1700

Data Index: 1419009 (Python Code)

Max Activating Token Index: 753

Text #4

Max Range: 2.8748. Min Range: -2.8748

Max Act: 2.8104. Min Act: -0.1699

Data Index: 292624 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 2.8748. Min Range: -2.8748

Max Act: 2.8121. Min Act: -0.1700

Data Index: 608723 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 2.8748. Min Range: -2.8748

Max Act: 2.8119. Min Act: -0.1700

Data Index: 72276 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 2.8748. Min Range: -2.8748

Max Act: 2.8168. Min Act: -0.1700

Data Index: 1129417 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 2.8748. Min Range: -2.8748

Max Act: 2.8018. Min Act: -0.1700

Data Index: 294172 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 2.8748. Min Range: -2.8748

Max Act: 2.8137. Min Act: -0.1699

Data Index: 828253 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 2.8748. Min Range: -2.8748

Max Act: 2.8041. Min Act: -0.1700

Data Index: 449053 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 2.8748. Min Range: -2.8748

Max Act: 2.7852. Min Act: -0.1700

Data Index: 526791 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 2.8748. Min Range: -2.8748

Max Act: 2.7943. Min Act: -0.1700

Data Index: 348286 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 2.8748. Min Range: -2.8748

Max Act: 2.7915. Min Act: -0.1699

Data Index: 984439 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 2.8748. Min Range: -2.8748

Max Act: 2.7771. Min Act: -0.1700

Data Index: 1298807 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 2.8748. Min Range: -2.8748

Max Act: 2.7686. Min Act: -0.1700

Data Index: 130410 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 2.8748. Min Range: -2.8748

Max Act: 2.7772. Min Act: -0.1700

Data Index: 1393914 (Python Code)

Max Activating Token Index: 926

Text #17

Max Range: 2.8748. Min Range: -2.8748

Max Act: 2.7626. Min Act: -0.1700

Data Index: 724098 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 2.8748. Min Range: -2.8748

Max Act: 2.7663. Min Act: -0.1700

Data Index: 945323 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 2.8748. Min Range: -2.8748

Max Act: 2.7594. Min Act: -0.1700

Data Index: 1126794 (C4 (Web Text))

Max Activating Token Index: 181