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

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

Neuron 1214 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: 3.4762. Min Range: -3.4762

Max Act: 3.4762. Min Act: -0.1700

Data Index: 846354 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.4531. Min Act: -0.1700

Data Index: 1162932 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.3887. Min Act: -0.1700

Data Index: 142741 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.3826. Min Act: -0.1700

Data Index: 58616 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.3429. Min Act: -0.1700

Data Index: 1112225 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.3294. Min Act: -0.1700

Data Index: 568988 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.2880. Min Act: -0.1700

Data Index: 777252 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.2940. Min Act: -0.1700

Data Index: 150280 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.2961. Min Act: -0.1700

Data Index: 978664 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.2472. Min Act: -0.1700

Data Index: 266406 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.2549. Min Act: -0.1700

Data Index: 631838 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.2202. Min Act: -0.1700

Data Index: 1159242 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.2417. Min Act: -0.1700

Data Index: 124976 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.2515. Min Act: -0.1700

Data Index: 1195087 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.2292. Min Act: -0.1699

Data Index: 975137 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.2430. Min Act: -0.1700

Data Index: 1032069 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.2018. Min Act: -0.1700

Data Index: 296051 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.2005. Min Act: -0.1700

Data Index: 401877 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.2211. Min Act: -0.1700

Data Index: 1140926 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.1851. Min Act: -0.1700

Data Index: 784275 (C4 (Web Text))

Max Activating Token Index: 674