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

Dataset: Open Web Text

Neuron 650 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: 4.0678. Min Range: -4.0678

Max Act: 4.0678. Min Act: -0.1700

Data Index: 3525636 (Open Web Text)

Max Activating Token Index: 18

Text #1

Max Range: 4.0678. Min Range: -4.0678

Max Act: 3.6962. Min Act: -0.1700

Data Index: 929222 (Open Web Text)

Max Activating Token Index: 606

Text #2

Max Range: 4.0678. Min Range: -4.0678

Max Act: 3.6743. Min Act: -0.1700

Data Index: 2049936 (Open Web Text)

Max Activating Token Index: 908

Text #3

Max Range: 4.0678. Min Range: -4.0678

Max Act: 3.6029. Min Act: -0.1700

Data Index: 8498829 (Open Web Text)

Max Activating Token Index: 497

Text #4

Max Range: 4.0678. Min Range: -4.0678

Max Act: 3.5847. Min Act: -0.1700

Data Index: 2317766 (Open Web Text)

Max Activating Token Index: 838

Text #5

Max Range: 4.0678. Min Range: -4.0678

Max Act: 3.5817. Min Act: -0.1700

Data Index: 3755096 (Open Web Text)

Max Activating Token Index: 957

Text #6

Max Range: 4.0678. Min Range: -4.0678

Max Act: 3.5420. Min Act: -0.1700

Data Index: 3240796 (Open Web Text)

Max Activating Token Index: 587

Text #7

Max Range: 4.0678. Min Range: -4.0678

Max Act: 3.5467. Min Act: -0.1700

Data Index: 7808960 (Open Web Text)

Max Activating Token Index: 650

Text #8

Max Range: 4.0678. Min Range: -4.0678

Max Act: 3.5480. Min Act: -0.1700

Data Index: 7659914 (Open Web Text)

Max Activating Token Index: 326

Text #9

Max Range: 4.0678. Min Range: -4.0678

Max Act: 3.5521. Min Act: -0.1700

Data Index: 4458108 (Open Web Text)

Max Activating Token Index: 77

Text #10

Max Range: 4.0678. Min Range: -4.0678

Max Act: 3.5186. Min Act: -0.1700

Data Index: 1778723 (Open Web Text)

Max Activating Token Index: 711

Text #11

Max Range: 4.0678. Min Range: -4.0678

Max Act: 3.5142. Min Act: -0.1700

Data Index: 2708325 (Open Web Text)

Max Activating Token Index: 310

Text #12

Max Range: 4.0678. Min Range: -4.0678

Max Act: 3.5255. Min Act: -0.1700

Data Index: 6104264 (Open Web Text)

Max Activating Token Index: 635

Text #13

Max Range: 4.0678. Min Range: -4.0678

Max Act: 3.5301. Min Act: -0.1700

Data Index: 1577525 (Open Web Text)

Max Activating Token Index: 206

Text #14

Max Range: 4.0678. Min Range: -4.0678

Max Act: 3.5424. Min Act: -0.1700

Data Index: 1445515 (Open Web Text)

Max Activating Token Index: 872

Text #15

Max Range: 4.0678. Min Range: -4.0678

Max Act: 3.5364. Min Act: -0.1700

Data Index: 3049376 (Open Web Text)

Max Activating Token Index: 342

Text #16

Max Range: 4.0678. Min Range: -4.0678

Max Act: 3.5098. Min Act: -0.1700

Data Index: 5298816 (Open Web Text)

Max Activating Token Index: 120

Text #17

Max Range: 4.0678. Min Range: -4.0678

Max Act: 3.4943. Min Act: -0.1700

Data Index: 6138309 (Open Web Text)

Max Activating Token Index: 848

Text #18

Max Range: 4.0678. Min Range: -4.0678

Max Act: 3.4903. Min Act: -0.1700

Data Index: 3540323 (Open Web Text)

Max Activating Token Index: 554

Text #19

Max Range: 4.0678. Min Range: -4.0678

Max Act: 3.4609. Min Act: -0.1700

Data Index: 7784971 (Open Web Text)

Max Activating Token Index: 846