Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1278 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.3166. Min Range: -5.3166

Max Act: 5.3166. Min Act: -0.1700

Data Index: 201306 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 5.3166. Min Range: -5.3166

Max Act: 5.0353. Min Act: -0.1700

Data Index: 1317703 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 5.3166. Min Range: -5.3166

Max Act: 5.0041. Min Act: -0.1700

Data Index: 821226 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 5.3166. Min Range: -5.3166

Max Act: 5.0041. Min Act: -0.1700

Data Index: 103034 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 5.3166. Min Range: -5.3166

Max Act: 4.9416. Min Act: -0.1700

Data Index: 568983 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 5.3166. Min Range: -5.3166

Max Act: 4.9728. Min Act: -0.1700

Data Index: 324120 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 5.3166. Min Range: -5.3166

Max Act: 5.0353. Min Act: -0.1700

Data Index: 1246190 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 5.3166. Min Range: -5.3166

Max Act: 4.9728. Min Act: -0.1700

Data Index: 7714 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 5.3166. Min Range: -5.3166

Max Act: 4.8791. Min Act: -0.1700

Data Index: 909784 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 5.3166. Min Range: -5.3166

Max Act: 4.9416. Min Act: -0.1700

Data Index: 141748 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 5.3166. Min Range: -5.3166

Max Act: 5.0041. Min Act: -0.1700

Data Index: 1184607 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 5.3166. Min Range: -5.3166

Max Act: 4.9728. Min Act: -0.1700

Data Index: 283052 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 5.3166. Min Range: -5.3166

Max Act: 4.9103. Min Act: -0.1700

Data Index: 985918 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 5.3166. Min Range: -5.3166

Max Act: 4.8791. Min Act: -0.1700

Data Index: 556170 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 5.3166. Min Range: -5.3166

Max Act: 4.8478. Min Act: -0.1700

Data Index: 398147 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 5.3166. Min Range: -5.3166

Max Act: 4.9103. Min Act: -0.1700

Data Index: 1019705 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 5.3166. Min Range: -5.3166

Max Act: 4.8478. Min Act: -0.1700

Data Index: 1338591 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 5.3166. Min Range: -5.3166

Max Act: 4.8166. Min Act: -0.1700

Data Index: 62163 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 5.3166. Min Range: -5.3166

Max Act: 4.8791. Min Act: -0.1700

Data Index: 251225 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 5.3166. Min Range: -5.3166

Max Act: 4.8166. Min Act: -0.1700

Data Index: 727353 (C4 (Web Text))

Max Activating Token Index: 71