Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 919 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.0356. Min Range: -5.0356

Max Act: 5.0356. Min Act: -0.1700

Data Index: 82984 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 5.0356. Min Range: -5.0356

Max Act: 4.9731. Min Act: -0.1700

Data Index: 1196941 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 5.0356. Min Range: -5.0356

Max Act: 4.8481. Min Act: -0.1700

Data Index: 933130 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 5.0356. Min Range: -5.0356

Max Act: 4.7856. Min Act: -0.1700

Data Index: 1076400 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 5.0356. Min Range: -5.0356

Max Act: 4.7543. Min Act: -0.1700

Data Index: 409965 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 5.0356. Min Range: -5.0356

Max Act: 4.7856. Min Act: -0.1700

Data Index: 846544 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 5.0356. Min Range: -5.0356

Max Act: 4.7856. Min Act: -0.1700

Data Index: 937464 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 5.0356. Min Range: -5.0356

Max Act: 4.7856. Min Act: -0.1700

Data Index: 349958 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 5.0356. Min Range: -5.0356

Max Act: 4.7543. Min Act: -0.1700

Data Index: 12676 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 5.0356. Min Range: -5.0356

Max Act: 4.6918. Min Act: -0.1700

Data Index: 1316851 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 5.0356. Min Range: -5.0356

Max Act: 4.6918. Min Act: -0.1700

Data Index: 1019881 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 5.0356. Min Range: -5.0356

Max Act: 4.8168. Min Act: -0.1700

Data Index: 233112 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 5.0356. Min Range: -5.0356

Max Act: 4.7231. Min Act: -0.1700

Data Index: 1077651 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 5.0356. Min Range: -5.0356

Max Act: 4.6918. Min Act: -0.1700

Data Index: 689601 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 5.0356. Min Range: -5.0356

Max Act: 4.6606. Min Act: -0.1700

Data Index: 930547 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 5.0356. Min Range: -5.0356

Max Act: 4.6293. Min Act: -0.1700

Data Index: 250077 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 5.0356. Min Range: -5.0356

Max Act: 4.6606. Min Act: -0.1700

Data Index: 736330 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 5.0356. Min Range: -5.0356

Max Act: 4.7543. Min Act: -0.1700

Data Index: 516715 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 5.0356. Min Range: -5.0356

Max Act: 4.5668. Min Act: -0.1700

Data Index: 831763 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 5.0356. Min Range: -5.0356

Max Act: 4.6293. Min Act: -0.1700

Data Index: 1064687 (C4 (Web Text))

Max Activating Token Index: 991