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

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

Neuron 1936 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: 3.1929. Min Range: -3.1929

Max Act: 3.1929. Min Act: -0.1700

Data Index: 161910 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 3.1929. Min Range: -3.1929

Max Act: 3.1473. Min Act: -0.1700

Data Index: 401520 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 3.1929. Min Range: -3.1929

Max Act: 3.1223. Min Act: -0.1700

Data Index: 836479 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 3.1929. Min Range: -3.1929

Max Act: 3.1159. Min Act: -0.1700

Data Index: 794387 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 3.1929. Min Range: -3.1929

Max Act: 3.0922. Min Act: -0.1700

Data Index: 704793 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 3.1929. Min Range: -3.1929

Max Act: 3.0772. Min Act: -0.1700

Data Index: 733020 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 3.1929. Min Range: -3.1929

Max Act: 3.0545. Min Act: -0.1700

Data Index: 690774 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 3.1929. Min Range: -3.1929

Max Act: 3.0593. Min Act: -0.1700

Data Index: 1201878 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 3.1929. Min Range: -3.1929

Max Act: 3.0412. Min Act: -0.1700

Data Index: 345392 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 3.1929. Min Range: -3.1929

Max Act: 3.0459. Min Act: -0.1700

Data Index: 172682 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 3.1929. Min Range: -3.1929

Max Act: 3.0226. Min Act: -0.1700

Data Index: 798585 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 3.1929. Min Range: -3.1929

Max Act: 3.0099. Min Act: -0.1700

Data Index: 698695 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 3.1929. Min Range: -3.1929

Max Act: 3.0016. Min Act: -0.1700

Data Index: 1036438 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 3.1929. Min Range: -3.1929

Max Act: 2.9928. Min Act: -0.1700

Data Index: 14442 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 3.1929. Min Range: -3.1929

Max Act: 2.9816. Min Act: -0.1700

Data Index: 439811 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 3.1929. Min Range: -3.1929

Max Act: 2.9850. Min Act: -0.1700

Data Index: 288237 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 3.1929. Min Range: -3.1929

Max Act: 2.9777. Min Act: -0.1700

Data Index: 479141 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 3.1929. Min Range: -3.1929

Max Act: 2.9809. Min Act: -0.1700

Data Index: 579974 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 3.1929. Min Range: -3.1929

Max Act: 2.9676. Min Act: -0.1700

Data Index: 920496 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 3.1929. Min Range: -3.1929

Max Act: 2.9732. Min Act: -0.1700

Data Index: 351923 (C4 (Web Text))

Max Activating Token Index: 867