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

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

Neuron 1415 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4176. Min Range: -3.4176

Max Act: 3.4176. Min Act: -0.1700

Data Index: 60171 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 3.4176. Min Range: -3.4176

Max Act: 3.2763. Min Act: -0.1700

Data Index: 1278355 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 3.4176. Min Range: -3.4176

Max Act: 3.2763. Min Act: -0.1700

Data Index: 1081649 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 3.4176. Min Range: -3.4176

Max Act: 3.2606. Min Act: -0.1700

Data Index: 216912 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 3.4176. Min Range: -3.4176

Max Act: 3.2763. Min Act: -0.1700

Data Index: 65478 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 3.4176. Min Range: -3.4176

Max Act: 3.2449. Min Act: -0.1700

Data Index: 724510 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 3.4176. Min Range: -3.4176

Max Act: 3.2134. Min Act: -0.1700

Data Index: 80870 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 3.4176. Min Range: -3.4176

Max Act: 3.2134. Min Act: -0.1700

Data Index: 150551 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 3.4176. Min Range: -3.4176

Max Act: 3.1820. Min Act: -0.1700

Data Index: 243750 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 3.4176. Min Range: -3.4176

Max Act: 3.2134. Min Act: -0.1700

Data Index: 1325446 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 3.4176. Min Range: -3.4176

Max Act: 3.2134. Min Act: -0.1700

Data Index: 310611 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 3.4176. Min Range: -3.4176

Max Act: 3.1820. Min Act: -0.1700

Data Index: 805906 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 3.4176. Min Range: -3.4176

Max Act: 3.1977. Min Act: -0.1700

Data Index: 808531 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 3.4176. Min Range: -3.4176

Max Act: 3.1977. Min Act: -0.1700

Data Index: 574005 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 3.4176. Min Range: -3.4176

Max Act: 3.1662. Min Act: -0.1700

Data Index: 338319 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 3.4176. Min Range: -3.4176

Max Act: 3.1662. Min Act: -0.1700

Data Index: 1265597 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 3.4176. Min Range: -3.4176

Max Act: 3.1505. Min Act: -0.1700

Data Index: 1292429 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 3.4176. Min Range: -3.4176

Max Act: 3.1820. Min Act: -0.1700

Data Index: 754921 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 3.4176. Min Range: -3.4176

Max Act: 3.1820. Min Act: -0.1700

Data Index: 935636 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 3.4176. Min Range: -3.4176

Max Act: 3.1662. Min Act: -0.1700

Data Index: 857161 (C4 (Web Text))

Max Activating Token Index: 886