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

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

Neuron 1702 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.7284. Min Act: -0.1700

Data Index: 1161865 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.6032. Min Act: -0.1700

Data Index: 583116 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.5249. Min Act: -0.1700

Data Index: 145491 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.5249. Min Act: -0.1700

Data Index: 99998 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.4935. Min Act: -0.1700

Data Index: 976538 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.4622. Min Act: -0.1700

Data Index: 1083939 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.5092. Min Act: -0.1700

Data Index: 893998 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.4622. Min Act: -0.1700

Data Index: 1122632 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.4151. Min Act: -0.1700

Data Index: 427248 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.4308. Min Act: -0.1700

Data Index: 118328 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.3995. Min Act: -0.1700

Data Index: 1227101 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.4151. Min Act: -0.1700

Data Index: 1271915 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.3995. Min Act: -0.1700

Data Index: 916969 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.3995. Min Act: -0.1700

Data Index: 496198 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.3995. Min Act: -0.1700

Data Index: 653860 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.3681. Min Act: -0.1700

Data Index: 1340221 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.3524. Min Act: -0.1700

Data Index: 1295927 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.3681. Min Act: -0.1700

Data Index: 503198 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.3367. Min Act: -0.1700

Data Index: 441139 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.3367. Min Act: -0.1700

Data Index: 1022025 (C4 (Web Text))

Max Activating Token Index: 440