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

Dataset: Open Web Text

Neuron 259 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: 3.2896. Min Range: -3.2896

Max Act: 3.2896. Min Act: -0.1700

Data Index: 4458857 (Open Web Text)

Max Activating Token Index: 864

Text #1

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.2787. Min Act: -0.1700

Data Index: 4439437 (Open Web Text)

Max Activating Token Index: 400

Text #2

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.2636. Min Act: -0.1700

Data Index: 6142300 (Open Web Text)

Max Activating Token Index: 197

Text #3

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.2513. Min Act: -0.1700

Data Index: 3797824 (Open Web Text)

Max Activating Token Index: 926

Text #4

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.2249. Min Act: -0.1700

Data Index: 315646 (Open Web Text)

Max Activating Token Index: 237

Text #5

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.2371. Min Act: -0.1700

Data Index: 4809010 (Open Web Text)

Max Activating Token Index: 205

Text #6

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.2416. Min Act: -0.1700

Data Index: 3670595 (Open Web Text)

Max Activating Token Index: 236

Text #7

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.2659. Min Act: -0.1700

Data Index: 4809009 (Open Web Text)

Max Activating Token Index: 1017

Text #8

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.2493. Min Act: -0.1700

Data Index: 4220084 (Open Web Text)

Max Activating Token Index: 64

Text #9

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1582. Min Act: -0.1700

Data Index: 3385940 (Open Web Text)

Max Activating Token Index: 188

Text #10

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1678. Min Act: -0.1700

Data Index: 1706213 (Open Web Text)

Max Activating Token Index: 87

Text #11

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1395. Min Act: -0.1700

Data Index: 3720776 (Open Web Text)

Max Activating Token Index: 1013

Text #12

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1727. Min Act: -0.1700

Data Index: 6921934 (Open Web Text)

Max Activating Token Index: 486

Text #13

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1404. Min Act: -0.1700

Data Index: 4047204 (Open Web Text)

Max Activating Token Index: 136

Text #14

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1489. Min Act: -0.1700

Data Index: 3962318 (Open Web Text)

Max Activating Token Index: 798

Text #15

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1540. Min Act: -0.1700

Data Index: 2905576 (Open Web Text)

Max Activating Token Index: 463

Text #16

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1857. Min Act: -0.1700

Data Index: 3278226 (Open Web Text)

Max Activating Token Index: 778

Text #17

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1632. Min Act: -0.1700

Data Index: 5163218 (Open Web Text)

Max Activating Token Index: 23

Text #18

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1420. Min Act: -0.1700

Data Index: 1519414 (Open Web Text)

Max Activating Token Index: 13

Text #19

Max Range: 3.2896. Min Range: -3.2896

Max Act: 3.1330. Min Act: -0.1700

Data Index: 439344 (Open Web Text)

Max Activating Token Index: 205