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

Dataset: Open Web Text

Neuron 372 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: 5.4765. Min Range: -5.4765

Max Act: 5.4765. Min Act: -0.1700

Data Index: 1630755 (Open Web Text)

Max Activating Token Index: 570

Text #1

Max Range: 5.4765. Min Range: -5.4765

Max Act: 5.4017. Min Act: -0.1700

Data Index: 747814 (Open Web Text)

Max Activating Token Index: 552

Text #2

Max Range: 5.4765. Min Range: -5.4765

Max Act: 5.4402. Min Act: -0.1700

Data Index: 5526000 (Open Web Text)

Max Activating Token Index: 812

Text #3

Max Range: 5.4765. Min Range: -5.4765

Max Act: 5.2395. Min Act: -0.1700

Data Index: 6262165 (Open Web Text)

Max Activating Token Index: 164

Text #4

Max Range: 5.4765. Min Range: -5.4765

Max Act: 5.2275. Min Act: -0.1700

Data Index: 2361667 (Open Web Text)

Max Activating Token Index: 501

Text #5

Max Range: 5.4765. Min Range: -5.4765

Max Act: 5.2071. Min Act: -0.1700

Data Index: 2068917 (Open Web Text)

Max Activating Token Index: 806

Text #6

Max Range: 5.4765. Min Range: -5.4765

Max Act: 5.1106. Min Act: -0.1700

Data Index: 6931120 (Open Web Text)

Max Activating Token Index: 759

Text #7

Max Range: 5.4765. Min Range: -5.4765

Max Act: 5.2062. Min Act: -0.1700

Data Index: 2141659 (Open Web Text)

Max Activating Token Index: 381

Text #8

Max Range: 5.4765. Min Range: -5.4765

Max Act: 5.0455. Min Act: -0.1700

Data Index: 6509128 (Open Web Text)

Max Activating Token Index: 985

Text #9

Max Range: 5.4765. Min Range: -5.4765

Max Act: 5.1189. Min Act: -0.1700

Data Index: 6396713 (Open Web Text)

Max Activating Token Index: 120

Text #10

Max Range: 5.4765. Min Range: -5.4765

Max Act: 5.1672. Min Act: -0.1700

Data Index: 7779214 (Open Web Text)

Max Activating Token Index: 447

Text #11

Max Range: 5.4765. Min Range: -5.4765

Max Act: 5.0808. Min Act: -0.1700

Data Index: 1021387 (Open Web Text)

Max Activating Token Index: 275

Text #12

Max Range: 5.4765. Min Range: -5.4765

Max Act: 5.1644. Min Act: -0.1700

Data Index: 4511364 (Open Web Text)

Max Activating Token Index: 372

Text #13

Max Range: 5.4765. Min Range: -5.4765

Max Act: 5.1312. Min Act: -0.1700

Data Index: 1386632 (Open Web Text)

Max Activating Token Index: 561

Text #14

Max Range: 5.4765. Min Range: -5.4765

Max Act: 5.1134. Min Act: -0.1700

Data Index: 7713732 (Open Web Text)

Max Activating Token Index: 501

Text #15

Max Range: 5.4765. Min Range: -5.4765

Max Act: 5.1046. Min Act: -0.1700

Data Index: 1214314 (Open Web Text)

Max Activating Token Index: 431

Text #16

Max Range: 5.4765. Min Range: -5.4765

Max Act: 5.0722. Min Act: -0.1700

Data Index: 3522489 (Open Web Text)

Max Activating Token Index: 652

Text #17

Max Range: 5.4765. Min Range: -5.4765

Max Act: 5.1177. Min Act: -0.1700

Data Index: 5669679 (Open Web Text)

Max Activating Token Index: 482

Text #18

Max Range: 5.4765. Min Range: -5.4765

Max Act: 5.0608. Min Act: -0.1700

Data Index: 4911908 (Open Web Text)

Max Activating Token Index: 466

Text #19

Max Range: 5.4765. Min Range: -5.4765

Max Act: 5.1870. Min Act: -0.1700

Data Index: 779834 (Open Web Text)

Max Activating Token Index: 531