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

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

Neuron 686 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: 3.1931. Min Range: -3.1931

Max Act: 3.1931. Min Act: -0.1700

Data Index: 202590 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 3.1931. Min Range: -3.1931

Max Act: 3.1901. Min Act: -0.1700

Data Index: 674393 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 3.1931. Min Range: -3.1931

Max Act: 3.1538. Min Act: -0.1697

Data Index: 189952 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 3.1931. Min Range: -3.1931

Max Act: 3.1410. Min Act: -0.1700

Data Index: 683190 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 3.1931. Min Range: -3.1931

Max Act: 3.1503. Min Act: -0.1700

Data Index: 1220000 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 3.1931. Min Range: -3.1931

Max Act: 3.1346. Min Act: -0.1700

Data Index: 1324769 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 3.1931. Min Range: -3.1931

Max Act: 3.1011. Min Act: -0.1700

Data Index: 805903 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 3.1931. Min Range: -3.1931

Max Act: 3.1144. Min Act: -0.1700

Data Index: 1330499 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 3.1931. Min Range: -3.1931

Max Act: 3.0976. Min Act: -0.1700

Data Index: 596680 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 3.1931. Min Range: -3.1931

Max Act: 3.1013. Min Act: -0.1700

Data Index: 388734 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 3.1931. Min Range: -3.1931

Max Act: 3.0929. Min Act: -0.1700

Data Index: 602321 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 3.1931. Min Range: -3.1931

Max Act: 3.0778. Min Act: -0.1700

Data Index: 539500 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 3.1931. Min Range: -3.1931

Max Act: 3.0939. Min Act: -0.1700

Data Index: 888719 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 3.1931. Min Range: -3.1931

Max Act: 3.0656. Min Act: -0.1700

Data Index: 813613 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 3.1931. Min Range: -3.1931

Max Act: 3.0703. Min Act: -0.1700

Data Index: 93127 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 3.1931. Min Range: -3.1931

Max Act: 3.0893. Min Act: -0.1700

Data Index: 192546 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 3.1931. Min Range: -3.1931

Max Act: 3.0796. Min Act: -0.1700

Data Index: 1097727 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 3.1931. Min Range: -3.1931

Max Act: 3.0650. Min Act: -0.1700

Data Index: 807263 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 3.1931. Min Range: -3.1931

Max Act: 3.0660. Min Act: -0.1700

Data Index: 849310 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 3.1931. Min Range: -3.1931

Max Act: 3.0594. Min Act: -0.1700

Data Index: 877284 (C4 (Web Text))

Max Activating Token Index: 46