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

Dataset: Open Web Text

Neuron 444 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: 3.0856. Min Range: -3.0856

Max Act: 3.0815. Min Act: -0.1700

Data Index: 6564304 (Open Web Text)

Max Activating Token Index: 583

Text #1

Max Range: 3.0856. Min Range: -3.0856

Max Act: 3.0856. Min Act: -0.1700

Data Index: 3171797 (Open Web Text)

Max Activating Token Index: 671

Text #2

Max Range: 3.0856. Min Range: -3.0856

Max Act: 3.0416. Min Act: -0.1700

Data Index: 4193075 (Open Web Text)

Max Activating Token Index: 929

Text #3

Max Range: 3.0856. Min Range: -3.0856

Max Act: 3.0657. Min Act: -0.1700

Data Index: 8170824 (Open Web Text)

Max Activating Token Index: 328

Text #4

Max Range: 3.0856. Min Range: -3.0856

Max Act: 3.0466. Min Act: -0.1700

Data Index: 7573517 (Open Web Text)

Max Activating Token Index: 852

Text #5

Max Range: 3.0856. Min Range: -3.0856

Max Act: 3.0351. Min Act: -0.1700

Data Index: 7587606 (Open Web Text)

Max Activating Token Index: 840

Text #6

Max Range: 3.0856. Min Range: -3.0856

Max Act: 3.0617. Min Act: -0.1700

Data Index: 6718194 (Open Web Text)

Max Activating Token Index: 464

Text #7

Max Range: 3.0856. Min Range: -3.0856

Max Act: 2.9927. Min Act: -0.1700

Data Index: 5343174 (Open Web Text)

Max Activating Token Index: 586

Text #8

Max Range: 3.0856. Min Range: -3.0856

Max Act: 3.0304. Min Act: -0.1700

Data Index: 3870522 (Open Web Text)

Max Activating Token Index: 111

Text #9

Max Range: 3.0856. Min Range: -3.0856

Max Act: 3.0056. Min Act: -0.1700

Data Index: 343898 (Open Web Text)

Max Activating Token Index: 255

Text #10

Max Range: 3.0856. Min Range: -3.0856

Max Act: 3.0408. Min Act: -0.1700

Data Index: 2312191 (Open Web Text)

Max Activating Token Index: 198

Text #11

Max Range: 3.0856. Min Range: -3.0856

Max Act: 2.9929. Min Act: -0.1700

Data Index: 3462908 (Open Web Text)

Max Activating Token Index: 48

Text #12

Max Range: 3.0856. Min Range: -3.0856

Max Act: 3.0019. Min Act: -0.1700

Data Index: 339556 (Open Web Text)

Max Activating Token Index: 373

Text #13

Max Range: 3.0856. Min Range: -3.0856

Max Act: 2.9675. Min Act: -0.1700

Data Index: 319334 (Open Web Text)

Max Activating Token Index: 980

Text #14

Max Range: 3.0856. Min Range: -3.0856

Max Act: 2.9841. Min Act: -0.1700

Data Index: 4247189 (Open Web Text)

Max Activating Token Index: 144

Text #15

Max Range: 3.0856. Min Range: -3.0856

Max Act: 2.9983. Min Act: -0.1700

Data Index: 1762056 (Open Web Text)

Max Activating Token Index: 416

Text #16

Max Range: 3.0856. Min Range: -3.0856

Max Act: 2.9789. Min Act: -0.1700

Data Index: 1995127 (Open Web Text)

Max Activating Token Index: 466

Text #17

Max Range: 3.0856. Min Range: -3.0856

Max Act: 2.9816. Min Act: -0.1700

Data Index: 4014154 (Open Web Text)

Max Activating Token Index: 576

Text #18

Max Range: 3.0856. Min Range: -3.0856

Max Act: 2.9860. Min Act: -0.1700

Data Index: 4841753 (Open Web Text)

Max Activating Token Index: 102

Text #19

Max Range: 3.0856. Min Range: -3.0856

Max Act: 2.9688. Min Act: -0.1700

Data Index: 1149118 (Open Web Text)

Max Activating Token Index: 423