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

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

Neuron 1335 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: 4.6961. Min Range: -4.6961

Max Act: 4.6961. Min Act: -0.1700

Data Index: 732908 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 4.6961. Min Range: -4.6961

Max Act: 4.6651. Min Act: -0.1700

Data Index: 504695 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 4.6961. Min Range: -4.6961

Max Act: 4.6376. Min Act: -0.1700

Data Index: 1153751 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 4.6961. Min Range: -4.6961

Max Act: 4.6234. Min Act: -0.1700

Data Index: 748843 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 4.6961. Min Range: -4.6961

Max Act: 4.5883. Min Act: -0.1700

Data Index: 1008529 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 4.6961. Min Range: -4.6961

Max Act: 4.6630. Min Act: -0.1700

Data Index: 1177456 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 4.6961. Min Range: -4.6961

Max Act: 4.6504. Min Act: -0.1700

Data Index: 461852 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 4.6961. Min Range: -4.6961

Max Act: 4.5945. Min Act: -0.1700

Data Index: 940289 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 4.6961. Min Range: -4.6961

Max Act: 4.5571. Min Act: -0.1700

Data Index: 1021319 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 4.6961. Min Range: -4.6961

Max Act: 4.5141. Min Act: -0.1700

Data Index: 1356051 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 4.6961. Min Range: -4.6961

Max Act: 4.5640. Min Act: -0.1700

Data Index: 866871 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 4.6961. Min Range: -4.6961

Max Act: 4.6068. Min Act: -0.1700

Data Index: 610297 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 4.6961. Min Range: -4.6961

Max Act: 4.5705. Min Act: -0.1700

Data Index: 420886 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 4.6961. Min Range: -4.6961

Max Act: 4.5593. Min Act: -0.1700

Data Index: 1080056 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 4.6961. Min Range: -4.6961

Max Act: 4.5488. Min Act: -0.1700

Data Index: 1088839 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 4.6961. Min Range: -4.6961

Max Act: 4.5747. Min Act: -0.1700

Data Index: 812504 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 4.6961. Min Range: -4.6961

Max Act: 4.5184. Min Act: -0.1700

Data Index: 1228130 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 4.6961. Min Range: -4.6961

Max Act: 4.5380. Min Act: -0.1700

Data Index: 1255093 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 4.6961. Min Range: -4.6961

Max Act: 4.5457. Min Act: -0.1700

Data Index: 1137177 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 4.6961. Min Range: -4.6961

Max Act: 4.4707. Min Act: -0.1700

Data Index: 730833 (C4 (Web Text))

Max Activating Token Index: 797