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

Dataset: Open Web Text

Neuron 1854 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: 4.3111. Min Range: -4.3111

Max Act: 4.3111. Min Act: -0.1700

Data Index: 8523678 (Open Web Text)

Max Activating Token Index: 895

Text #1

Max Range: 4.3111. Min Range: -4.3111

Max Act: 3.9746. Min Act: -0.1700

Data Index: 7057000 (Open Web Text)

Max Activating Token Index: 505

Text #2

Max Range: 4.3111. Min Range: -4.3111

Max Act: 3.9842. Min Act: -0.1700

Data Index: 3031839 (Open Web Text)

Max Activating Token Index: 466

Text #3

Max Range: 4.3111. Min Range: -4.3111

Max Act: 3.9507. Min Act: -0.1700

Data Index: 13366 (Open Web Text)

Max Activating Token Index: 818

Text #4

Max Range: 4.3111. Min Range: -4.3111

Max Act: 3.9132. Min Act: -0.1700

Data Index: 5790448 (Open Web Text)

Max Activating Token Index: 389

Text #5

Max Range: 4.3111. Min Range: -4.3111

Max Act: 3.7371. Min Act: -0.1700

Data Index: 2416865 (Open Web Text)

Max Activating Token Index: 277

Text #6

Max Range: 4.3111. Min Range: -4.3111

Max Act: 3.6978. Min Act: -0.1700

Data Index: 3069100 (Open Web Text)

Max Activating Token Index: 135

Text #7

Max Range: 4.3111. Min Range: -4.3111

Max Act: 3.6103. Min Act: -0.1700

Data Index: 3627240 (Open Web Text)

Max Activating Token Index: 113

Text #8

Max Range: 4.3111. Min Range: -4.3111

Max Act: 3.5062. Min Act: -0.1700

Data Index: 3898414 (Open Web Text)

Max Activating Token Index: 705

Text #9

Max Range: 4.3111. Min Range: -4.3111

Max Act: 3.5071. Min Act: -0.1700

Data Index: 8404616 (Open Web Text)

Max Activating Token Index: 238

Text #10

Max Range: 4.3111. Min Range: -4.3111

Max Act: 3.4569. Min Act: -0.1700

Data Index: 5857839 (Open Web Text)

Max Activating Token Index: 202

Text #11

Max Range: 4.3111. Min Range: -4.3111

Max Act: 3.4775. Min Act: -0.1700

Data Index: 6630776 (Open Web Text)

Max Activating Token Index: 168

Text #12

Max Range: 4.3111. Min Range: -4.3111

Max Act: 3.4613. Min Act: -0.1700

Data Index: 4609017 (Open Web Text)

Max Activating Token Index: 562

Text #13

Max Range: 4.3111. Min Range: -4.3111

Max Act: 3.4744. Min Act: -0.1700

Data Index: 8494281 (Open Web Text)

Max Activating Token Index: 1003

Text #14

Max Range: 4.3111. Min Range: -4.3111

Max Act: 3.4342. Min Act: -0.1700

Data Index: 3178128 (Open Web Text)

Max Activating Token Index: 568

Text #15

Max Range: 4.3111. Min Range: -4.3111

Max Act: 3.4338. Min Act: -0.1700

Data Index: 7719207 (Open Web Text)

Max Activating Token Index: 870

Text #16

Max Range: 4.3111. Min Range: -4.3111

Max Act: 3.4840. Min Act: -0.1700

Data Index: 5933821 (Open Web Text)

Max Activating Token Index: 504

Text #17

Max Range: 4.3111. Min Range: -4.3111

Max Act: 3.4503. Min Act: -0.1700

Data Index: 3245893 (Open Web Text)

Max Activating Token Index: 103

Text #18

Max Range: 4.3111. Min Range: -4.3111

Max Act: 3.4477. Min Act: -0.1700

Data Index: 5758371 (Open Web Text)

Max Activating Token Index: 206

Text #19

Max Range: 4.3111. Min Range: -4.3111

Max Act: 3.4398. Min Act: -0.1700

Data Index: 3889062 (Open Web Text)

Max Activating Token Index: 433