Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1782 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.0957. Min Range: -3.0957

Max Act: 3.0957. Min Act: -0.1700

Data Index: 335591 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 3.0957. Min Range: -3.0957

Max Act: 3.0326. Min Act: -0.1700

Data Index: 1316697 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 3.0957. Min Range: -3.0957

Max Act: 3.0010. Min Act: -0.1700

Data Index: 97525 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.9693. Min Act: -0.1700

Data Index: 895501 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.9693. Min Act: -0.1700

Data Index: 572543 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.9535. Min Act: -0.1700

Data Index: 484681 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.9377. Min Act: -0.1700

Data Index: 109412 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.9218. Min Act: -0.1700

Data Index: 999941 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.9218. Min Act: -0.1700

Data Index: 1268106 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.9218. Min Act: -0.1700

Data Index: 786030 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.9060. Min Act: -0.1700

Data Index: 833302 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.8901. Min Act: -0.1700

Data Index: 290155 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.8901. Min Act: -0.1700

Data Index: 978163 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.8742. Min Act: -0.1700

Data Index: 801844 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.8742. Min Act: -0.1700

Data Index: 1189272 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.8425. Min Act: -0.1700

Data Index: 977709 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.8584. Min Act: -0.1700

Data Index: 621155 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.8584. Min Act: -0.1700

Data Index: 1276943 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.8266. Min Act: -0.1700

Data Index: 466928 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 3.0957. Min Range: -3.0957

Max Act: 2.8425. Min Act: -0.1700

Data Index: 960056 (C4 (Web Text))

Max Activating Token Index: 948