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

Dataset: Open Web Text

Neuron 95 in Layer 6

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: 3.4902. Min Range: -3.4902

Max Act: 3.4902. Min Act: -0.1700

Data Index: 5218986 (Open Web Text)

Max Activating Token Index: 731

Text #1

Max Range: 3.4902. Min Range: -3.4902

Max Act: 3.4292. Min Act: -0.1700

Data Index: 2797136 (Open Web Text)

Max Activating Token Index: 182

Text #2

Max Range: 3.4902. Min Range: -3.4902

Max Act: 3.4064. Min Act: -0.1700

Data Index: 3635661 (Open Web Text)

Max Activating Token Index: 785

Text #3

Max Range: 3.4902. Min Range: -3.4902

Max Act: 3.3272. Min Act: -0.1700

Data Index: 2621583 (Open Web Text)

Max Activating Token Index: 231

Text #4

Max Range: 3.4902. Min Range: -3.4902

Max Act: 3.3332. Min Act: -0.1700

Data Index: 4940307 (Open Web Text)

Max Activating Token Index: 251

Text #5

Max Range: 3.4902. Min Range: -3.4902

Max Act: 3.3187. Min Act: -0.1700

Data Index: 2580450 (Open Web Text)

Max Activating Token Index: 49

Text #6

Max Range: 3.4902. Min Range: -3.4902

Max Act: 3.3129. Min Act: -0.1700

Data Index: 2652085 (Open Web Text)

Max Activating Token Index: 367

Text #7

Max Range: 3.4902. Min Range: -3.4902

Max Act: 3.3072. Min Act: -0.1700

Data Index: 1233942 (Open Web Text)

Max Activating Token Index: 376

Text #8

Max Range: 3.4902. Min Range: -3.4902

Max Act: 3.3149. Min Act: -0.1700

Data Index: 697360 (Open Web Text)

Max Activating Token Index: 296

Text #9

Max Range: 3.4902. Min Range: -3.4902

Max Act: 3.2927. Min Act: -0.1700

Data Index: 3509802 (Open Web Text)

Max Activating Token Index: 201

Text #10

Max Range: 3.4902. Min Range: -3.4902

Max Act: 3.2922. Min Act: -0.1700

Data Index: 1240735 (Open Web Text)

Max Activating Token Index: 677

Text #11

Max Range: 3.4902. Min Range: -3.4902

Max Act: 3.2680. Min Act: -0.1700

Data Index: 3014293 (Open Web Text)

Max Activating Token Index: 182

Text #12

Max Range: 3.4902. Min Range: -3.4902

Max Act: 3.2506. Min Act: -0.1700

Data Index: 4536855 (Open Web Text)

Max Activating Token Index: 955

Text #13

Max Range: 3.4902. Min Range: -3.4902

Max Act: 3.2764. Min Act: -0.1700

Data Index: 1048469 (Open Web Text)

Max Activating Token Index: 442

Text #14

Max Range: 3.4902. Min Range: -3.4902

Max Act: 3.2492. Min Act: -0.1700

Data Index: 1218509 (Open Web Text)

Max Activating Token Index: 655

Text #15

Max Range: 3.4902. Min Range: -3.4902

Max Act: 3.2350. Min Act: -0.1700

Data Index: 4222864 (Open Web Text)

Max Activating Token Index: 706

Text #16

Max Range: 3.4902. Min Range: -3.4902

Max Act: 3.2204. Min Act: -0.1700

Data Index: 6306876 (Open Web Text)

Max Activating Token Index: 537

Text #17

Max Range: 3.4902. Min Range: -3.4902

Max Act: 3.2353. Min Act: -0.1700

Data Index: 501062 (Open Web Text)

Max Activating Token Index: 163

Text #18

Max Range: 3.4902. Min Range: -3.4902

Max Act: 3.2738. Min Act: -0.1700

Data Index: 1267486 (Open Web Text)

Max Activating Token Index: 783

Text #19

Max Range: 3.4902. Min Range: -3.4902

Max Act: 3.2542. Min Act: -0.1700

Data Index: 2309275 (Open Web Text)

Max Activating Token Index: 183