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

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

Neuron 1189 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: 4.0858. Min Range: -4.0858

Max Act: 4.0858. Min Act: -0.1321

Data Index: 378740 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 4.0858. Min Range: -4.0858

Max Act: 3.9890. Min Act: -0.1646

Data Index: 911096 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 4.0858. Min Range: -4.0858

Max Act: 3.9103. Min Act: -0.1415

Data Index: 367384 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 4.0858. Min Range: -4.0858

Max Act: 3.9144. Min Act: -0.1481

Data Index: 248678 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 4.0858. Min Range: -4.0858

Max Act: 3.9102. Min Act: -0.1698

Data Index: 170629 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 4.0858. Min Range: -4.0858

Max Act: 3.8779. Min Act: -0.0296

Data Index: 33877 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 4.0858. Min Range: -4.0858

Max Act: 3.8794. Min Act: -0.0034

Data Index: 333317 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 4.0858. Min Range: -4.0858

Max Act: 3.8918. Min Act: -0.1672

Data Index: 956360 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 4.0858. Min Range: -4.0858

Max Act: 3.8573. Min Act: -0.1699

Data Index: 1348363 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 4.0858. Min Range: -4.0858

Max Act: 3.8505. Min Act: -0.1700

Data Index: 654467 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 4.0858. Min Range: -4.0858

Max Act: 3.8384. Min Act: -0.0034

Data Index: 413507 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 4.0858. Min Range: -4.0858

Max Act: 3.8194. Min Act: -0.1592

Data Index: 994262 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 4.0858. Min Range: -4.0858

Max Act: 3.8113. Min Act: -0.0786

Data Index: 924610 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 4.0858. Min Range: -4.0858

Max Act: 3.8060. Min Act: -0.1700

Data Index: 1103253 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 4.0858. Min Range: -4.0858

Max Act: 3.8071. Min Act: -0.1700

Data Index: 31379 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 4.0858. Min Range: -4.0858

Max Act: 3.7677. Min Act: -0.0034

Data Index: 990067 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 4.0858. Min Range: -4.0858

Max Act: 3.7904. Min Act: -0.0034

Data Index: 848723 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 4.0858. Min Range: -4.0858

Max Act: 3.7942. Min Act: -0.1700

Data Index: 897177 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 4.0858. Min Range: -4.0858

Max Act: 3.7928. Min Act: -0.1696

Data Index: 763854 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 4.0858. Min Range: -4.0858

Max Act: 3.7804. Min Act: -0.1700

Data Index: 730278 (C4 (Web Text))

Max Activating Token Index: 633