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

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

Neuron 739 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: 3.1029. Min Range: -3.1029

Max Act: 3.1010. Min Act: -0.1700

Data Index: 1343910 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 3.1029. Min Range: -3.1029

Max Act: 3.1029. Min Act: -0.1700

Data Index: 989899 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 3.1029. Min Range: -3.1029

Max Act: 3.0943. Min Act: -0.1700

Data Index: 832872 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 3.1029. Min Range: -3.1029

Max Act: 3.0469. Min Act: -0.1700

Data Index: 1076978 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 3.1029. Min Range: -3.1029

Max Act: 3.0385. Min Act: -0.1700

Data Index: 1167574 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 3.1029. Min Range: -3.1029

Max Act: 3.0570. Min Act: -0.1700

Data Index: 30494 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 3.1029. Min Range: -3.1029

Max Act: 3.0193. Min Act: -0.1700

Data Index: 226598 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 3.1029. Min Range: -3.1029

Max Act: 3.0008. Min Act: -0.1700

Data Index: 1040403 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 3.1029. Min Range: -3.1029

Max Act: 3.0128. Min Act: -0.1700

Data Index: 892259 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 3.1029. Min Range: -3.1029

Max Act: 3.0016. Min Act: -0.1700

Data Index: 528644 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 3.1029. Min Range: -3.1029

Max Act: 2.9882. Min Act: -0.1700

Data Index: 1202732 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 3.1029. Min Range: -3.1029

Max Act: 2.9989. Min Act: -0.1700

Data Index: 1176883 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 3.1029. Min Range: -3.1029

Max Act: 2.9884. Min Act: -0.1700

Data Index: 179945 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 3.1029. Min Range: -3.1029

Max Act: 2.9980. Min Act: -0.1700

Data Index: 85089 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 3.1029. Min Range: -3.1029

Max Act: 2.9920. Min Act: -0.1700

Data Index: 1114759 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 3.1029. Min Range: -3.1029

Max Act: 2.9964. Min Act: -0.1700

Data Index: 1122981 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 3.1029. Min Range: -3.1029

Max Act: 2.9860. Min Act: -0.1700

Data Index: 485566 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 3.1029. Min Range: -3.1029

Max Act: 2.9595. Min Act: -0.1700

Data Index: 1097076 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 3.1029. Min Range: -3.1029

Max Act: 2.9663. Min Act: -0.1700

Data Index: 924521 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 3.1029. Min Range: -3.1029

Max Act: 2.9615. Min Act: -0.1700

Data Index: 692890 (C4 (Web Text))

Max Activating Token Index: 829