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

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

Neuron 139 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: 2.7865. Min Range: -2.7865

Max Act: 2.7865. Min Act: -0.1700

Data Index: 232938 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.7731. Min Act: -0.1700

Data Index: 977041 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.7693. Min Act: -0.1700

Data Index: 187934 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.7464. Min Act: -0.1700

Data Index: 426897 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.6782. Min Act: -0.1700

Data Index: 963216 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.6560. Min Act: -0.1700

Data Index: 610334 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.6190. Min Act: -0.1700

Data Index: 1224452 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.6250. Min Act: -0.1700

Data Index: 431443 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.6182. Min Act: -0.1700

Data Index: 1002605 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.5952. Min Act: -0.1700

Data Index: 334792 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.5948. Min Act: -0.1700

Data Index: 857125 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.5809. Min Act: -0.1700

Data Index: 957807 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.5723. Min Act: -0.1700

Data Index: 943676 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.5763. Min Act: -0.1700

Data Index: 485963 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.5647. Min Act: -0.1700

Data Index: 811105 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.5553. Min Act: -0.1700

Data Index: 387692 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.5539. Min Act: -0.1700

Data Index: 1343894 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.5531. Min Act: -0.1700

Data Index: 546425 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.5537. Min Act: -0.1700

Data Index: 632403 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.5479. Min Act: -0.1700

Data Index: 117339 (C4 (Web Text))

Max Activating Token Index: 409