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

Dataset: Open Web Text

Neuron 283 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: 3.4204. Min Range: -3.4204

Max Act: 3.4204. Min Act: -0.1700

Data Index: 8449388 (Open Web Text)

Max Activating Token Index: 946

Text #1

Max Range: 3.4204. Min Range: -3.4204

Max Act: 3.3748. Min Act: -0.1700

Data Index: 5767054 (Open Web Text)

Max Activating Token Index: 218

Text #2

Max Range: 3.4204. Min Range: -3.4204

Max Act: 3.3469. Min Act: -0.1700

Data Index: 1947794 (Open Web Text)

Max Activating Token Index: 780

Text #3

Max Range: 3.4204. Min Range: -3.4204

Max Act: 3.3772. Min Act: -0.1700

Data Index: 6010573 (Open Web Text)

Max Activating Token Index: 890

Text #4

Max Range: 3.4204. Min Range: -3.4204

Max Act: 3.3784. Min Act: -0.1700

Data Index: 118870 (Open Web Text)

Max Activating Token Index: 718

Text #5

Max Range: 3.4204. Min Range: -3.4204

Max Act: 3.3260. Min Act: -0.1700

Data Index: 3968153 (Open Web Text)

Max Activating Token Index: 530

Text #6

Max Range: 3.4204. Min Range: -3.4204

Max Act: 3.3257. Min Act: -0.1700

Data Index: 20149 (Open Web Text)

Max Activating Token Index: 777

Text #7

Max Range: 3.4204. Min Range: -3.4204

Max Act: 3.3172. Min Act: -0.1700

Data Index: 7371715 (Open Web Text)

Max Activating Token Index: 515

Text #8

Max Range: 3.4204. Min Range: -3.4204

Max Act: 3.3121. Min Act: -0.1700

Data Index: 1429793 (Open Web Text)

Max Activating Token Index: 634

Text #9

Max Range: 3.4204. Min Range: -3.4204

Max Act: 3.3197. Min Act: -0.1700

Data Index: 8090772 (Open Web Text)

Max Activating Token Index: 377

Text #10

Max Range: 3.4204. Min Range: -3.4204

Max Act: 3.2818. Min Act: -0.1700

Data Index: 4909850 (Open Web Text)

Max Activating Token Index: 122

Text #11

Max Range: 3.4204. Min Range: -3.4204

Max Act: 3.3447. Min Act: -0.1700

Data Index: 1307141 (Open Web Text)

Max Activating Token Index: 742

Text #12

Max Range: 3.4204. Min Range: -3.4204

Max Act: 3.3007. Min Act: -0.1700

Data Index: 6714081 (Open Web Text)

Max Activating Token Index: 410

Text #13

Max Range: 3.4204. Min Range: -3.4204

Max Act: 3.2894. Min Act: -0.1700

Data Index: 1887123 (Open Web Text)

Max Activating Token Index: 116

Text #14

Max Range: 3.4204. Min Range: -3.4204

Max Act: 3.3176. Min Act: -0.1700

Data Index: 2648469 (Open Web Text)

Max Activating Token Index: 304

Text #15

Max Range: 3.4204. Min Range: -3.4204

Max Act: 3.2878. Min Act: -0.1700

Data Index: 3289689 (Open Web Text)

Max Activating Token Index: 191

Text #16

Max Range: 3.4204. Min Range: -3.4204

Max Act: 3.2680. Min Act: -0.1700

Data Index: 8083839 (Open Web Text)

Max Activating Token Index: 496

Text #17

Max Range: 3.4204. Min Range: -3.4204

Max Act: 3.2689. Min Act: -0.1700

Data Index: 2085297 (Open Web Text)

Max Activating Token Index: 367

Text #18

Max Range: 3.4204. Min Range: -3.4204

Max Act: 3.2679. Min Act: -0.1700

Data Index: 2470642 (Open Web Text)

Max Activating Token Index: 895

Text #19

Max Range: 3.4204. Min Range: -3.4204

Max Act: 3.3216. Min Act: -0.1700

Data Index: 4987128 (Open Web Text)

Max Activating Token Index: 953