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

Dataset: Open Web Text

Neuron 1228 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: 3.8702. Min Range: -3.8702

Max Act: 3.8702. Min Act: -0.1700

Data Index: 6093098 (Open Web Text)

Max Activating Token Index: 296

Text #1

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.7693. Min Act: -0.1700

Data Index: 2582126 (Open Web Text)

Max Activating Token Index: 312

Text #2

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.7656. Min Act: -0.1700

Data Index: 983334 (Open Web Text)

Max Activating Token Index: 111

Text #3

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.7528. Min Act: -0.1700

Data Index: 7363613 (Open Web Text)

Max Activating Token Index: 361

Text #4

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.7331. Min Act: -0.1700

Data Index: 8674040 (Open Web Text)

Max Activating Token Index: 318

Text #5

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.7589. Min Act: -0.1700

Data Index: 7904768 (Open Web Text)

Max Activating Token Index: 721

Text #6

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.7176. Min Act: -0.1700

Data Index: 150496 (Open Web Text)

Max Activating Token Index: 668

Text #7

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.7124. Min Act: -0.1700

Data Index: 3137591 (Open Web Text)

Max Activating Token Index: 395

Text #8

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.7143. Min Act: -0.1700

Data Index: 1954366 (Open Web Text)

Max Activating Token Index: 994

Text #9

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.7193. Min Act: -0.1700

Data Index: 3506861 (Open Web Text)

Max Activating Token Index: 858

Text #10

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.6584. Min Act: -0.1700

Data Index: 651635 (Open Web Text)

Max Activating Token Index: 518

Text #11

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.6944. Min Act: -0.1700

Data Index: 5261941 (Open Web Text)

Max Activating Token Index: 645

Text #12

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.7111. Min Act: -0.1700

Data Index: 2767696 (Open Web Text)

Max Activating Token Index: 554

Text #13

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.6864. Min Act: -0.1700

Data Index: 7017545 (Open Web Text)

Max Activating Token Index: 771

Text #14

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.7051. Min Act: -0.1700

Data Index: 170734 (Open Web Text)

Max Activating Token Index: 254

Text #15

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.7152. Min Act: -0.1700

Data Index: 8569470 (Open Web Text)

Max Activating Token Index: 668

Text #16

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.6946. Min Act: -0.1700

Data Index: 2534024 (Open Web Text)

Max Activating Token Index: 853

Text #17

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.6790. Min Act: -0.1700

Data Index: 5819720 (Open Web Text)

Max Activating Token Index: 359

Text #18

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.6869. Min Act: -0.1700

Data Index: 8345905 (Open Web Text)

Max Activating Token Index: 326

Text #19

Max Range: 3.8702. Min Range: -3.8702

Max Act: 3.6430. Min Act: -0.1700

Data Index: 6118857 (Open Web Text)

Max Activating Token Index: 575