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

Dataset: Open Web Text

Neuron 2111 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: 4.1077. Min Range: -4.1077

Max Act: 4.1077. Min Act: -0.1700

Data Index: 7308545 (Open Web Text)

Max Activating Token Index: 676

Text #1

Max Range: 4.1077. Min Range: -4.1077

Max Act: 4.0610. Min Act: -0.1700

Data Index: 5600981 (Open Web Text)

Max Activating Token Index: 228

Text #2

Max Range: 4.1077. Min Range: -4.1077

Max Act: 4.0395. Min Act: -0.1700

Data Index: 6632112 (Open Web Text)

Max Activating Token Index: 232

Text #3

Max Range: 4.1077. Min Range: -4.1077

Max Act: 3.9955. Min Act: -0.1700

Data Index: 5155505 (Open Web Text)

Max Activating Token Index: 381

Text #4

Max Range: 4.1077. Min Range: -4.1077

Max Act: 4.0081. Min Act: -0.1700

Data Index: 5844363 (Open Web Text)

Max Activating Token Index: 45

Text #5

Max Range: 4.1077. Min Range: -4.1077

Max Act: 3.9913. Min Act: -0.1700

Data Index: 1128486 (Open Web Text)

Max Activating Token Index: 65

Text #6

Max Range: 4.1077. Min Range: -4.1077

Max Act: 3.9622. Min Act: -0.1700

Data Index: 5270885 (Open Web Text)

Max Activating Token Index: 243

Text #7

Max Range: 4.1077. Min Range: -4.1077

Max Act: 3.9512. Min Act: -0.1700

Data Index: 1095936 (Open Web Text)

Max Activating Token Index: 981

Text #8

Max Range: 4.1077. Min Range: -4.1077

Max Act: 3.9306. Min Act: -0.1700

Data Index: 436518 (Open Web Text)

Max Activating Token Index: 641

Text #9

Max Range: 4.1077. Min Range: -4.1077

Max Act: 3.9286. Min Act: -0.1700

Data Index: 5030035 (Open Web Text)

Max Activating Token Index: 300

Text #10

Max Range: 4.1077. Min Range: -4.1077

Max Act: 3.9504. Min Act: -0.1700

Data Index: 4715385 (Open Web Text)

Max Activating Token Index: 225

Text #11

Max Range: 4.1077. Min Range: -4.1077

Max Act: 3.9180. Min Act: -0.1700

Data Index: 8793728 (Open Web Text)

Max Activating Token Index: 497

Text #12

Max Range: 4.1077. Min Range: -4.1077

Max Act: 3.9300. Min Act: -0.1700

Data Index: 4020094 (Open Web Text)

Max Activating Token Index: 113

Text #13

Max Range: 4.1077. Min Range: -4.1077

Max Act: 3.9414. Min Act: -0.1700

Data Index: 6632110 (Open Web Text)

Max Activating Token Index: 390

Text #14

Max Range: 4.1077. Min Range: -4.1077

Max Act: 3.9348. Min Act: -0.1700

Data Index: 5925483 (Open Web Text)

Max Activating Token Index: 521

Text #15

Max Range: 4.1077. Min Range: -4.1077

Max Act: 3.9280. Min Act: -0.1700

Data Index: 5177273 (Open Web Text)

Max Activating Token Index: 997

Text #16

Max Range: 4.1077. Min Range: -4.1077

Max Act: 3.9038. Min Act: -0.1700

Data Index: 2279762 (Open Web Text)

Max Activating Token Index: 416

Text #17

Max Range: 4.1077. Min Range: -4.1077

Max Act: 3.9257. Min Act: -0.1700

Data Index: 3101759 (Open Web Text)

Max Activating Token Index: 723

Text #18

Max Range: 4.1077. Min Range: -4.1077

Max Act: 3.9021. Min Act: -0.1700

Data Index: 752770 (Open Web Text)

Max Activating Token Index: 566

Text #19

Max Range: 4.1077. Min Range: -4.1077

Max Act: 3.8883. Min Act: -0.1700

Data Index: 5089682 (Open Web Text)

Max Activating Token Index: 172