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

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

Neuron 756 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: 3.3979. Min Range: -3.3979

Max Act: 3.3979. Min Act: -0.1700

Data Index: 1014443 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 3.3979. Min Range: -3.3979

Max Act: 3.3027. Min Act: -0.1700

Data Index: 511947 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 3.3979. Min Range: -3.3979

Max Act: 3.2050. Min Act: -0.1700

Data Index: 332593 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 3.3979. Min Range: -3.3979

Max Act: 3.2007. Min Act: -0.1700

Data Index: 901514 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 3.3979. Min Range: -3.3979

Max Act: 3.1730. Min Act: -0.1700

Data Index: 1302064 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 3.3979. Min Range: -3.3979

Max Act: 3.1739. Min Act: -0.1700

Data Index: 63839 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 3.3979. Min Range: -3.3979

Max Act: 3.1569. Min Act: -0.1700

Data Index: 1012276 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 3.3979. Min Range: -3.3979

Max Act: 3.1118. Min Act: -0.1700

Data Index: 1474745 (Python Code)

Max Activating Token Index: 359

Text #8

Max Range: 3.3979. Min Range: -3.3979

Max Act: 3.1156. Min Act: -0.1700

Data Index: 1070968 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 3.3979. Min Range: -3.3979

Max Act: 3.1077. Min Act: -0.1700

Data Index: 1283597 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 3.3979. Min Range: -3.3979

Max Act: 3.0720. Min Act: -0.1700

Data Index: 56067 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 3.3979. Min Range: -3.3979

Max Act: 3.1028. Min Act: -0.1700

Data Index: 1100301 (C4 (Web Text))

Max Activating Token Index: 553

Text #12

Max Range: 3.3979. Min Range: -3.3979

Max Act: 3.0924. Min Act: -0.1700

Data Index: 784613 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 3.3979. Min Range: -3.3979

Max Act: 3.1253. Min Act: -0.1700

Data Index: 1084060 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 3.3979. Min Range: -3.3979

Max Act: 3.0724. Min Act: -0.1700

Data Index: 1096535 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 3.3979. Min Range: -3.3979

Max Act: 3.0696. Min Act: -0.1700

Data Index: 425230 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 3.3979. Min Range: -3.3979

Max Act: 3.1038. Min Act: -0.1700

Data Index: 916112 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 3.3979. Min Range: -3.3979

Max Act: 3.0703. Min Act: -0.1700

Data Index: 636753 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 3.3979. Min Range: -3.3979

Max Act: 3.0343. Min Act: -0.1700

Data Index: 883128 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 3.3979. Min Range: -3.3979

Max Act: 3.0267. Min Act: -0.1700

Data Index: 156527 (C4 (Web Text))

Max Activating Token Index: 211