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

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

Neuron 1785 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: 2.9547. Min Range: -2.9547

Max Act: 2.9547. Min Act: -0.1700

Data Index: 232309 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 2.9547. Min Range: -2.9547

Max Act: 2.9176. Min Act: -0.1700

Data Index: 659520 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 2.9547. Min Range: -2.9547

Max Act: 2.8677. Min Act: -0.1700

Data Index: 1056318 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 2.9547. Min Range: -2.9547

Max Act: 2.8149. Min Act: -0.1700

Data Index: 773675 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 2.9547. Min Range: -2.9547

Max Act: 2.7989. Min Act: -0.1700

Data Index: 1594905 (Python Code)

Max Activating Token Index: 507

Text #5

Max Range: 2.9547. Min Range: -2.9547

Max Act: 2.7922. Min Act: -0.1700

Data Index: 371267 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 2.9547. Min Range: -2.9547

Max Act: 2.8075. Min Act: -0.1700

Data Index: 405642 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 2.9547. Min Range: -2.9547

Max Act: 2.7848. Min Act: -0.1700

Data Index: 918297 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 2.9547. Min Range: -2.9547

Max Act: 2.7825. Min Act: -0.1700

Data Index: 1310506 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 2.9547. Min Range: -2.9547

Max Act: 2.7796. Min Act: -0.1700

Data Index: 1507620 (Python Code)

Max Activating Token Index: 798

Text #10

Max Range: 2.9547. Min Range: -2.9547

Max Act: 2.7728. Min Act: -0.1700

Data Index: 768395 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 2.9547. Min Range: -2.9547

Max Act: 2.7406. Min Act: -0.1700

Data Index: 1133080 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 2.9547. Min Range: -2.9547

Max Act: 2.7422. Min Act: -0.1700

Data Index: 104192 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 2.9547. Min Range: -2.9547

Max Act: 2.7221. Min Act: -0.1700

Data Index: 1536428 (Python Code)

Max Activating Token Index: 62

Text #14

Max Range: 2.9547. Min Range: -2.9547

Max Act: 2.7351. Min Act: -0.1700

Data Index: 198459 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 2.9547. Min Range: -2.9547

Max Act: 2.7226. Min Act: -0.1700

Data Index: 207154 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 2.9547. Min Range: -2.9547

Max Act: 2.7330. Min Act: -0.1700

Data Index: 17667 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 2.9547. Min Range: -2.9547

Max Act: 2.7384. Min Act: -0.1700

Data Index: 971040 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 2.9547. Min Range: -2.9547

Max Act: 2.7389. Min Act: -0.1700

Data Index: 424116 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 2.9547. Min Range: -2.9547

Max Act: 2.7064. Min Act: -0.1700

Data Index: 631132 (C4 (Web Text))

Max Activating Token Index: 509