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

Dataset: Open Web Text

Neuron 991 in Layer 3

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: 4.0613. Min Range: -4.0613

Max Act: 4.0613. Min Act: -0.1700

Data Index: 6833061 (Open Web Text)

Max Activating Token Index: 186

Text #1

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.9952. Min Act: -0.1700

Data Index: 6830723 (Open Web Text)

Max Activating Token Index: 396

Text #2

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.9752. Min Act: -0.1700

Data Index: 1315920 (Open Web Text)

Max Activating Token Index: 763

Text #3

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.9139. Min Act: -0.1700

Data Index: 3711075 (Open Web Text)

Max Activating Token Index: 495

Text #4

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.9635. Min Act: -0.1700

Data Index: 1591307 (Open Web Text)

Max Activating Token Index: 920

Text #5

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.9245. Min Act: -0.1700

Data Index: 1955156 (Open Web Text)

Max Activating Token Index: 785

Text #6

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.8756. Min Act: -0.1700

Data Index: 7743909 (Open Web Text)

Max Activating Token Index: 537

Text #7

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.8943. Min Act: -0.1700

Data Index: 4280194 (Open Web Text)

Max Activating Token Index: 421

Text #8

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.9342. Min Act: -0.1700

Data Index: 1297290 (Open Web Text)

Max Activating Token Index: 351

Text #9

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.8820. Min Act: -0.1700

Data Index: 3217832 (Open Web Text)

Max Activating Token Index: 504

Text #10

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.9124. Min Act: -0.1700

Data Index: 1161889 (Open Web Text)

Max Activating Token Index: 121

Text #11

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.9236. Min Act: -0.1700

Data Index: 356510 (Open Web Text)

Max Activating Token Index: 694

Text #12

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.9044. Min Act: -0.1700

Data Index: 3627323 (Open Web Text)

Max Activating Token Index: 267

Text #13

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.8523. Min Act: -0.1700

Data Index: 1154462 (Open Web Text)

Max Activating Token Index: 704

Text #14

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.8781. Min Act: -0.1700

Data Index: 6548828 (Open Web Text)

Max Activating Token Index: 476

Text #15

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.8830. Min Act: -0.1700

Data Index: 3372215 (Open Web Text)

Max Activating Token Index: 642

Text #16

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.8862. Min Act: -0.1700

Data Index: 6223916 (Open Web Text)

Max Activating Token Index: 483

Text #17

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.8829. Min Act: -0.1700

Data Index: 4709885 (Open Web Text)

Max Activating Token Index: 354

Text #18

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.8393. Min Act: -0.1700

Data Index: 895723 (Open Web Text)

Max Activating Token Index: 611

Text #19

Max Range: 4.0613. Min Range: -4.0613

Max Act: 3.8879. Min Act: -0.1700

Data Index: 2736370 (Open Web Text)

Max Activating Token Index: 586