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

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

Neuron 520 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: 2.9400. Min Range: -2.9400

Max Act: 2.9400. Min Act: -0.1700

Data Index: 1062533 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 2.9400. Min Range: -2.9400

Max Act: 2.9054. Min Act: -0.1504

Data Index: 922806 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 2.9400. Min Range: -2.9400

Max Act: 2.8981. Min Act: -0.1700

Data Index: 486614 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 2.9400. Min Range: -2.9400

Max Act: 2.8810. Min Act: -0.1644

Data Index: 1111276 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 2.9400. Min Range: -2.9400

Max Act: 2.8844. Min Act: -0.1699

Data Index: 215720 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 2.9400. Min Range: -2.9400

Max Act: 2.8694. Min Act: -0.1700

Data Index: 643530 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 2.9400. Min Range: -2.9400

Max Act: 2.8572. Min Act: -0.1700

Data Index: 1003297 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 2.9400. Min Range: -2.9400

Max Act: 2.8458. Min Act: -0.1699

Data Index: 777922 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 2.9400. Min Range: -2.9400

Max Act: 2.8650. Min Act: -0.1699

Data Index: 103472 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 2.9400. Min Range: -2.9400

Max Act: 2.8163. Min Act: -0.1700

Data Index: 270871 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 2.9400. Min Range: -2.9400

Max Act: 2.8265. Min Act: -0.1700

Data Index: 1252171 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 2.9400. Min Range: -2.9400

Max Act: 2.8135. Min Act: -0.1700

Data Index: 1189761 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 2.9400. Min Range: -2.9400

Max Act: 2.7956. Min Act: -0.1700

Data Index: 30976 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 2.9400. Min Range: -2.9400

Max Act: 2.7985. Min Act: -0.1700

Data Index: 432186 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 2.9400. Min Range: -2.9400

Max Act: 2.8062. Min Act: -0.1696

Data Index: 91000 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 2.9400. Min Range: -2.9400

Max Act: 2.7794. Min Act: -0.1700

Data Index: 762364 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 2.9400. Min Range: -2.9400

Max Act: 2.7808. Min Act: -0.1700

Data Index: 229156 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 2.9400. Min Range: -2.9400

Max Act: 2.7824. Min Act: -0.1697

Data Index: 1034269 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 2.9400. Min Range: -2.9400

Max Act: 2.7925. Min Act: -0.1700

Data Index: 602040 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 2.9400. Min Range: -2.9400

Max Act: 2.7919. Min Act: -0.1700

Data Index: 532823 (C4 (Web Text))

Max Activating Token Index: 610