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

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

Neuron 1183 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: 5.8043. Min Range: -5.8043

Max Act: 5.7106. Min Act: -0.1700

Data Index: 1110767 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 5.8043. Min Range: -5.8043

Max Act: 5.8043. Min Act: -0.1700

Data Index: 511466 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 5.8043. Min Range: -5.8043

Max Act: 5.3981. Min Act: -0.1700

Data Index: 902752 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 5.8043. Min Range: -5.8043

Max Act: 5.3668. Min Act: -0.1700

Data Index: 1309158 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 5.8043. Min Range: -5.8043

Max Act: 5.3981. Min Act: -0.1700

Data Index: 638487 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 5.8043. Min Range: -5.8043

Max Act: 5.2731. Min Act: -0.1700

Data Index: 843042 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 5.8043. Min Range: -5.8043

Max Act: 5.2418. Min Act: -0.1700

Data Index: 1178010 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 5.8043. Min Range: -5.8043

Max Act: 5.3043. Min Act: -0.1700

Data Index: 37255 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 5.8043. Min Range: -5.8043

Max Act: 5.2418. Min Act: -0.1700

Data Index: 1259955 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 5.8043. Min Range: -5.8043

Max Act: 5.2418. Min Act: -0.1700

Data Index: 95577 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 5.8043. Min Range: -5.8043

Max Act: 5.2106. Min Act: -0.1700

Data Index: 111852 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 5.8043. Min Range: -5.8043

Max Act: 5.2418. Min Act: -0.1700

Data Index: 389056 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 5.8043. Min Range: -5.8043

Max Act: 5.2731. Min Act: -0.1700

Data Index: 1293489 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 5.8043. Min Range: -5.8043

Max Act: 5.1793. Min Act: -0.1700

Data Index: 1340 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 5.8043. Min Range: -5.8043

Max Act: 5.2106. Min Act: -0.1687

Data Index: 381799 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 5.8043. Min Range: -5.8043

Max Act: 5.1793. Min Act: -0.1700

Data Index: 1342718 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 5.8043. Min Range: -5.8043

Max Act: 5.1481. Min Act: -0.1700

Data Index: 90873 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 5.8043. Min Range: -5.8043

Max Act: 5.1793. Min Act: -0.1700

Data Index: 1132516 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 5.8043. Min Range: -5.8043

Max Act: 5.1481. Min Act: -0.1699

Data Index: 902711 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 5.8043. Min Range: -5.8043

Max Act: 5.1168. Min Act: -0.1700

Data Index: 794831 (C4 (Web Text))

Max Activating Token Index: 997