Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 668 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.0938. Min Range: -4.0938

Max Act: 4.0938. Min Act: -0.1699

Data Index: 209511 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 4.0938. Min Range: -4.0938

Max Act: 4.0213. Min Act: -0.1700

Data Index: 1015114 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 4.0938. Min Range: -4.0938

Max Act: 3.9820. Min Act: -0.1700

Data Index: 237339 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 4.0938. Min Range: -4.0938

Max Act: 3.9616. Min Act: -0.1700

Data Index: 327629 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 4.0938. Min Range: -4.0938

Max Act: 3.9046. Min Act: -0.1700

Data Index: 495834 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 4.0938. Min Range: -4.0938

Max Act: 3.9085. Min Act: -0.1700

Data Index: 860088 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 4.0938. Min Range: -4.0938

Max Act: 3.9034. Min Act: -0.1700

Data Index: 959790 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 4.0938. Min Range: -4.0938

Max Act: 3.8975. Min Act: -0.1700

Data Index: 273594 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 4.0938. Min Range: -4.0938

Max Act: 3.8947. Min Act: -0.1700

Data Index: 995635 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 4.0938. Min Range: -4.0938

Max Act: 3.9146. Min Act: -0.1700

Data Index: 577180 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 4.0938. Min Range: -4.0938

Max Act: 3.8851. Min Act: -0.1700

Data Index: 1028970 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 4.0938. Min Range: -4.0938

Max Act: 3.8888. Min Act: -0.1700

Data Index: 1216222 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 4.0938. Min Range: -4.0938

Max Act: 3.8625. Min Act: -0.1700

Data Index: 21726 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 4.0938. Min Range: -4.0938

Max Act: 3.8555. Min Act: -0.1700

Data Index: 668689 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 4.0938. Min Range: -4.0938

Max Act: 3.8596. Min Act: -0.1700

Data Index: 724131 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 4.0938. Min Range: -4.0938

Max Act: 3.8606. Min Act: -0.1699

Data Index: 1342070 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 4.0938. Min Range: -4.0938

Max Act: 3.8569. Min Act: -0.1699

Data Index: 934049 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 4.0938. Min Range: -4.0938

Max Act: 3.8489. Min Act: -0.1700

Data Index: 1111709 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 4.0938. Min Range: -4.0938

Max Act: 3.8100. Min Act: -0.1699

Data Index: 769897 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 4.0938. Min Range: -4.0938

Max Act: 3.8126. Min Act: -0.1700

Data Index: 1059023 (C4 (Web Text))

Max Activating Token Index: 149