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

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

Neuron 321 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.7016. Min Act: -0.1700

Data Index: 1173731 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.4981. Min Act: -0.1700

Data Index: 811127 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.5294. Min Act: -0.1700

Data Index: 788276 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.4510. Min Act: -0.1700

Data Index: 984790 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.4510. Min Act: -0.1700

Data Index: 1094981 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.4510. Min Act: -0.1700

Data Index: 323664 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.4510. Min Act: -0.1700

Data Index: 771343 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.4354. Min Act: -0.1700

Data Index: 1026099 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.3883. Min Act: -0.1700

Data Index: 1217400 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.4040. Min Act: -0.1700

Data Index: 1232443 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.4040. Min Act: -0.1700

Data Index: 1191958 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.4510. Min Act: -0.1700

Data Index: 1093168 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.4197. Min Act: -0.1700

Data Index: 943967 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.4040. Min Act: -0.1700

Data Index: 637345 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.4354. Min Act: -0.1700

Data Index: 139098 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.4040. Min Act: -0.1700

Data Index: 842286 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.4040. Min Act: -0.1700

Data Index: 1167509 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.3883. Min Act: -0.1700

Data Index: 190679 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.4040. Min Act: -0.1700

Data Index: 683026 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.4197. Min Act: -0.1700

Data Index: 1175938 (C4 (Web Text))

Max Activating Token Index: 600