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

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

Neuron 1329 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: 3.8427. Min Range: -3.8427

Max Act: 3.8427. Min Act: -0.1700

Data Index: 94122 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.8196. Min Act: -0.1700

Data Index: 739753 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.7388. Min Act: -0.1700

Data Index: 1265684 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.7639. Min Act: -0.1700

Data Index: 145013 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.7104. Min Act: -0.1700

Data Index: 608730 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.7080. Min Act: -0.1700

Data Index: 449569 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.6881. Min Act: -0.1700

Data Index: 1067471 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.6793. Min Act: -0.1700

Data Index: 757853 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.6594. Min Act: -0.1700

Data Index: 269627 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.6686. Min Act: -0.1700

Data Index: 1289415 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.6526. Min Act: -0.1700

Data Index: 1151152 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.6303. Min Act: -0.1700

Data Index: 1038150 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.6355. Min Act: -0.1700

Data Index: 1124314 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.6277. Min Act: -0.1700

Data Index: 776408 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.6316. Min Act: -0.1700

Data Index: 1136822 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.6328. Min Act: -0.1700

Data Index: 1165021 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.6169. Min Act: -0.1700

Data Index: 1098507 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.6141. Min Act: -0.1700

Data Index: 601074 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.5934. Min Act: -0.1700

Data Index: 220355 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 3.8427. Min Range: -3.8427

Max Act: 3.5992. Min Act: -0.1700

Data Index: 1232639 (C4 (Web Text))

Max Activating Token Index: 342