Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1283 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.9860. Min Range: -4.9860

Max Act: 4.9860. Min Act: -0.1700

Data Index: 200085 (Open Web Text)

Max Activating Token Index: 661

Text #1

Max Range: 4.9860. Min Range: -4.9860

Max Act: 4.7499. Min Act: -0.1700

Data Index: 3487355 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 4.9860. Min Range: -4.9860

Max Act: 4.7598. Min Act: -0.1700

Data Index: 6813209 (Open Web Text)

Max Activating Token Index: 993

Text #3

Max Range: 4.9860. Min Range: -4.9860

Max Act: 4.7428. Min Act: -0.1700

Data Index: 6043041 (Open Web Text)

Max Activating Token Index: 831

Text #4

Max Range: 4.9860. Min Range: -4.9860

Max Act: 4.7391. Min Act: -0.1700

Data Index: 7869120 (Open Web Text)

Max Activating Token Index: 1017

Text #5

Max Range: 4.9860. Min Range: -4.9860

Max Act: 4.7506. Min Act: -0.1700

Data Index: 2788088 (Open Web Text)

Max Activating Token Index: 1021

Text #6

Max Range: 4.9860. Min Range: -4.9860

Max Act: 4.7015. Min Act: -0.1700

Data Index: 5936919 (Open Web Text)

Max Activating Token Index: 987

Text #7

Max Range: 4.9860. Min Range: -4.9860

Max Act: 4.7450. Min Act: -0.1700

Data Index: 1057173 (Open Web Text)

Max Activating Token Index: 976

Text #8

Max Range: 4.9860. Min Range: -4.9860

Max Act: 4.6968. Min Act: -0.1700

Data Index: 2553445 (Open Web Text)

Max Activating Token Index: 76

Text #9

Max Range: 4.9860. Min Range: -4.9860

Max Act: 4.6645. Min Act: -0.1700

Data Index: 683903 (Open Web Text)

Max Activating Token Index: 1013

Text #10

Max Range: 4.9860. Min Range: -4.9860

Max Act: 4.6478. Min Act: -0.1700

Data Index: 7865758 (Open Web Text)

Max Activating Token Index: 1000

Text #11

Max Range: 4.9860. Min Range: -4.9860

Max Act: 4.6942. Min Act: -0.1700

Data Index: 199204 (Open Web Text)

Max Activating Token Index: 570

Text #12

Max Range: 4.9860. Min Range: -4.9860

Max Act: 4.6429. Min Act: -0.1700

Data Index: 8548089 (Open Web Text)

Max Activating Token Index: 772

Text #13

Max Range: 4.9860. Min Range: -4.9860

Max Act: 4.6363. Min Act: -0.1700

Data Index: 2599447 (Open Web Text)

Max Activating Token Index: 624

Text #14

Max Range: 4.9860. Min Range: -4.9860

Max Act: 4.6496. Min Act: -0.1700

Data Index: 2615931 (Open Web Text)

Max Activating Token Index: 992

Text #15

Max Range: 4.9860. Min Range: -4.9860

Max Act: 4.6216. Min Act: -0.1700

Data Index: 3580719 (Open Web Text)

Max Activating Token Index: 664

Text #16

Max Range: 4.9860. Min Range: -4.9860

Max Act: 4.6532. Min Act: -0.1700

Data Index: 6167743 (Open Web Text)

Max Activating Token Index: 335

Text #17

Max Range: 4.9860. Min Range: -4.9860

Max Act: 4.6309. Min Act: -0.1700

Data Index: 5953852 (Open Web Text)

Max Activating Token Index: 1013

Text #18

Max Range: 4.9860. Min Range: -4.9860

Max Act: 4.6341. Min Act: -0.1700

Data Index: 4631591 (Open Web Text)

Max Activating Token Index: 881

Text #19

Max Range: 4.9860. Min Range: -4.9860

Max Act: 4.6180. Min Act: -0.1700

Data Index: 3469313 (Open Web Text)

Max Activating Token Index: 900