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

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

Neuron 1652 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: 3.2449. Min Range: -3.2449

Max Act: 3.2449. Min Act: -0.1700

Data Index: 537781 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 3.2449. Min Range: -3.2449

Max Act: 3.1969. Min Act: -0.1700

Data Index: 1515437 (Python Code)

Max Activating Token Index: 613

Text #2

Max Range: 3.2449. Min Range: -3.2449

Max Act: 3.1935. Min Act: -0.1700

Data Index: 1572587 (Python Code)

Max Activating Token Index: 498

Text #3

Max Range: 3.2449. Min Range: -3.2449

Max Act: 3.1594. Min Act: -0.1700

Data Index: 1419612 (Python Code)

Max Activating Token Index: 74

Text #4

Max Range: 3.2449. Min Range: -3.2449

Max Act: 3.1615. Min Act: -0.1700

Data Index: 1494723 (Python Code)

Max Activating Token Index: 240

Text #5

Max Range: 3.2449. Min Range: -3.2449

Max Act: 3.1413. Min Act: -0.1700

Data Index: 955269 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 3.2449. Min Range: -3.2449

Max Act: 3.1316. Min Act: -0.1700

Data Index: 1568195 (Python Code)

Max Activating Token Index: 1013

Text #7

Max Range: 3.2449. Min Range: -3.2449

Max Act: 3.1088. Min Act: -0.1700

Data Index: 1510841 (Python Code)

Max Activating Token Index: 25

Text #8

Max Range: 3.2449. Min Range: -3.2449

Max Act: 3.1220. Min Act: -0.1700

Data Index: 1635962 (Python Code)

Max Activating Token Index: 599

Text #9

Max Range: 3.2449. Min Range: -3.2449

Max Act: 3.1084. Min Act: -0.1700

Data Index: 1633687 (Python Code)

Max Activating Token Index: 148

Text #10

Max Range: 3.2449. Min Range: -3.2449

Max Act: 3.0894. Min Act: -0.1700

Data Index: 1478810 (Python Code)

Max Activating Token Index: 349

Text #11

Max Range: 3.2449. Min Range: -3.2449

Max Act: 3.1050. Min Act: -0.1700

Data Index: 1503669 (Python Code)

Max Activating Token Index: 60

Text #12

Max Range: 3.2449. Min Range: -3.2449

Max Act: 3.0796. Min Act: -0.1700

Data Index: 1529669 (Python Code)

Max Activating Token Index: 476

Text #13

Max Range: 3.2449. Min Range: -3.2449

Max Act: 3.0859. Min Act: -0.1700

Data Index: 1097543 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 3.2449. Min Range: -3.2449

Max Act: 3.0855. Min Act: -0.1700

Data Index: 247212 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 3.2449. Min Range: -3.2449

Max Act: 3.0806. Min Act: -0.1700

Data Index: 1293766 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 3.2449. Min Range: -3.2449

Max Act: 3.0740. Min Act: -0.1700

Data Index: 1555104 (Python Code)

Max Activating Token Index: 15

Text #17

Max Range: 3.2449. Min Range: -3.2449

Max Act: 3.0678. Min Act: -0.1700

Data Index: 1391231 (Python Code)

Max Activating Token Index: 988

Text #18

Max Range: 3.2449. Min Range: -3.2449

Max Act: 3.0757. Min Act: -0.1700

Data Index: 1410401 (Python Code)

Max Activating Token Index: 763

Text #19

Max Range: 3.2449. Min Range: -3.2449

Max Act: 3.0879. Min Act: -0.1700

Data Index: 1515982 (Python Code)

Max Activating Token Index: 526