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

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

Neuron 53 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.4438. Min Act: -0.1700

Data Index: 706489 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.4125. Min Act: -0.1700

Data Index: 1109195 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.3654. Min Act: -0.1700

Data Index: 1143610 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.2869. Min Act: -0.1700

Data Index: 1223890 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.2083. Min Act: -0.1700

Data Index: 180529 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.2083. Min Act: -0.1700

Data Index: 825842 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.1926. Min Act: -0.1700

Data Index: 456845 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.1926. Min Act: -0.1700

Data Index: 395518 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.1768. Min Act: -0.1700

Data Index: 37938 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.1768. Min Act: -0.1700

Data Index: 1228144 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.1453. Min Act: -0.1700

Data Index: 1198994 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.1453. Min Act: -0.1700

Data Index: 1002002 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.1296. Min Act: -0.1700

Data Index: 1217703 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.1138. Min Act: -0.1700

Data Index: 1236906 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.0981. Min Act: -0.1700

Data Index: 1234184 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.0823. Min Act: -0.1700

Data Index: 748159 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.0823. Min Act: -0.1700

Data Index: 825872 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.0665. Min Act: -0.1700

Data Index: 1056346 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.0823. Min Act: -0.1700

Data Index: 713389 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 3.4438. Min Range: -3.4438

Max Act: 3.0823. Min Act: -0.1700

Data Index: 328637 (C4 (Web Text))

Max Activating Token Index: 15