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

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

Neuron 1102 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: 3.1712. Min Range: -3.1712

Max Act: 3.1670. Min Act: -0.1700

Data Index: 1541136 (Python Code)

Max Activating Token Index: 299

Text #1

Max Range: 3.1712. Min Range: -3.1712

Max Act: 3.1712. Min Act: -0.1700

Data Index: 928346 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 3.1712. Min Range: -3.1712

Max Act: 3.1603. Min Act: -0.1699

Data Index: 1553516 (Python Code)

Max Activating Token Index: 983

Text #3

Max Range: 3.1712. Min Range: -3.1712

Max Act: 3.1450. Min Act: -0.1670

Data Index: 1527155 (Python Code)

Max Activating Token Index: 470

Text #4

Max Range: 3.1712. Min Range: -3.1712

Max Act: 3.0310. Min Act: -0.1700

Data Index: 1364994 (Python Code)

Max Activating Token Index: 406

Text #5

Max Range: 3.1712. Min Range: -3.1712

Max Act: 3.0156. Min Act: -0.1700

Data Index: 1140899 (C4 (Web Text))

Max Activating Token Index: 580

Text #6

Max Range: 3.1712. Min Range: -3.1712

Max Act: 3.0151. Min Act: -0.1700

Data Index: 1537827 (Python Code)

Max Activating Token Index: 727

Text #7

Max Range: 3.1712. Min Range: -3.1712

Max Act: 3.0184. Min Act: -0.1700

Data Index: 651590 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 3.1712. Min Range: -3.1712

Max Act: 2.9933. Min Act: -0.1698

Data Index: 1481051 (Python Code)

Max Activating Token Index: 526

Text #9

Max Range: 3.1712. Min Range: -3.1712

Max Act: 2.9961. Min Act: -0.1695

Data Index: 942137 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 3.1712. Min Range: -3.1712

Max Act: 3.0013. Min Act: -0.1700

Data Index: 224999 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 3.1712. Min Range: -3.1712

Max Act: 2.9928. Min Act: -0.1699

Data Index: 1381377 (Python Code)

Max Activating Token Index: 449

Text #12

Max Range: 3.1712. Min Range: -3.1712

Max Act: 2.9932. Min Act: -0.1700

Data Index: 747483 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 3.1712. Min Range: -3.1712

Max Act: 2.9771. Min Act: -0.1700

Data Index: 1115276 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 3.1712. Min Range: -3.1712

Max Act: 2.9752. Min Act: -0.1692

Data Index: 757930 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 3.1712. Min Range: -3.1712

Max Act: 2.9777. Min Act: -0.1700

Data Index: 1382023 (Python Code)

Max Activating Token Index: 143

Text #16

Max Range: 3.1712. Min Range: -3.1712

Max Act: 2.9553. Min Act: -0.1698

Data Index: 1235221 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 3.1712. Min Range: -3.1712

Max Act: 2.9412. Min Act: -0.1700

Data Index: 1244749 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 3.1712. Min Range: -3.1712

Max Act: 2.9268. Min Act: -0.1699

Data Index: 1559896 (Python Code)

Max Activating Token Index: 657

Text #19

Max Range: 3.1712. Min Range: -3.1712

Max Act: 2.9526. Min Act: -0.1698

Data Index: 1570588 (Python Code)

Max Activating Token Index: 230