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

Dataset: Open Web Text

Neuron 2465 in Layer 1

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: 6.2333. Min Range: -6.2333

Max Act: 6.2333. Min Act: -0.1700

Data Index: 6990498 (Open Web Text)

Max Activating Token Index: 1014

Text #1

Max Range: 6.2333. Min Range: -6.2333

Max Act: 6.1889. Min Act: -0.1700

Data Index: 2495286 (Open Web Text)

Max Activating Token Index: 192

Text #2

Max Range: 6.2333. Min Range: -6.2333

Max Act: 6.1505. Min Act: -0.1700

Data Index: 4809677 (Open Web Text)

Max Activating Token Index: 806

Text #3

Max Range: 6.2333. Min Range: -6.2333

Max Act: 6.1955. Min Act: -0.1700

Data Index: 2993263 (Open Web Text)

Max Activating Token Index: 737

Text #4

Max Range: 6.2333. Min Range: -6.2333

Max Act: 6.1762. Min Act: -0.1700

Data Index: 2347233 (Open Web Text)

Max Activating Token Index: 45

Text #5

Max Range: 6.2333. Min Range: -6.2333

Max Act: 6.1599. Min Act: -0.1700

Data Index: 7170415 (Open Web Text)

Max Activating Token Index: 144

Text #6

Max Range: 6.2333. Min Range: -6.2333

Max Act: 6.1232. Min Act: -0.1700

Data Index: 2993264 (Open Web Text)

Max Activating Token Index: 92

Text #7

Max Range: 6.2333. Min Range: -6.2333

Max Act: 6.1196. Min Act: -0.1700

Data Index: 8214658 (Open Web Text)

Max Activating Token Index: 490

Text #8

Max Range: 6.2333. Min Range: -6.2333

Max Act: 6.0798. Min Act: -0.1700

Data Index: 3033861 (Open Web Text)

Max Activating Token Index: 639

Text #9

Max Range: 6.2333. Min Range: -6.2333

Max Act: 6.0723. Min Act: -0.1700

Data Index: 2564897 (Open Web Text)

Max Activating Token Index: 185

Text #10

Max Range: 6.2333. Min Range: -6.2333

Max Act: 6.0813. Min Act: -0.1700

Data Index: 3342777 (Open Web Text)

Max Activating Token Index: 714

Text #11

Max Range: 6.2333. Min Range: -6.2333

Max Act: 6.0730. Min Act: -0.1700

Data Index: 8166910 (Open Web Text)

Max Activating Token Index: 643

Text #12

Max Range: 6.2333. Min Range: -6.2333

Max Act: 6.0740. Min Act: -0.1700

Data Index: 3072378 (Open Web Text)

Max Activating Token Index: 655

Text #13

Max Range: 6.2333. Min Range: -6.2333

Max Act: 6.0712. Min Act: -0.1700

Data Index: 4139550 (Open Web Text)

Max Activating Token Index: 243

Text #14

Max Range: 6.2333. Min Range: -6.2333

Max Act: 6.0698. Min Act: -0.1700

Data Index: 5696720 (Open Web Text)

Max Activating Token Index: 61

Text #15

Max Range: 6.2333. Min Range: -6.2333

Max Act: 6.0701. Min Act: -0.1700

Data Index: 5106721 (Open Web Text)

Max Activating Token Index: 299

Text #16

Max Range: 6.2333. Min Range: -6.2333

Max Act: 6.0869. Min Act: -0.1700

Data Index: 1664762 (Open Web Text)

Max Activating Token Index: 633

Text #17

Max Range: 6.2333. Min Range: -6.2333

Max Act: 6.0806. Min Act: -0.1700

Data Index: 6849378 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 6.2333. Min Range: -6.2333

Max Act: 6.0516. Min Act: -0.1700

Data Index: 6486030 (Open Web Text)

Max Activating Token Index: 101

Text #19

Max Range: 6.2333. Min Range: -6.2333

Max Act: 6.0629. Min Act: -0.1700

Data Index: 3481875 (Open Web Text)

Max Activating Token Index: 769