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

Dataset: Open Web Text

Neuron 264 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: 6.0196. Min Range: -6.0196

Max Act: 6.0196. Min Act: -0.1700

Data Index: 3913903 (Open Web Text)

Max Activating Token Index: 881

Text #1

Max Range: 6.0196. Min Range: -6.0196

Max Act: 5.8857. Min Act: -0.1700

Data Index: 7906363 (Open Web Text)

Max Activating Token Index: 915

Text #2

Max Range: 6.0196. Min Range: -6.0196

Max Act: 5.8631. Min Act: -0.1700

Data Index: 8491081 (Open Web Text)

Max Activating Token Index: 174

Text #3

Max Range: 6.0196. Min Range: -6.0196

Max Act: 5.8337. Min Act: -0.1700

Data Index: 4002349 (Open Web Text)

Max Activating Token Index: 697

Text #4

Max Range: 6.0196. Min Range: -6.0196

Max Act: 5.8652. Min Act: -0.1700

Data Index: 3593310 (Open Web Text)

Max Activating Token Index: 450

Text #5

Max Range: 6.0196. Min Range: -6.0196

Max Act: 5.7882. Min Act: -0.1700

Data Index: 1134236 (Open Web Text)

Max Activating Token Index: 456

Text #6

Max Range: 6.0196. Min Range: -6.0196

Max Act: 5.8292. Min Act: -0.1700

Data Index: 6327493 (Open Web Text)

Max Activating Token Index: 236

Text #7

Max Range: 6.0196. Min Range: -6.0196

Max Act: 5.7951. Min Act: -0.1700

Data Index: 3710652 (Open Web Text)

Max Activating Token Index: 376

Text #8

Max Range: 6.0196. Min Range: -6.0196

Max Act: 5.7542. Min Act: -0.1700

Data Index: 747537 (Open Web Text)

Max Activating Token Index: 153

Text #9

Max Range: 6.0196. Min Range: -6.0196

Max Act: 5.7907. Min Act: -0.1700

Data Index: 7086693 (Open Web Text)

Max Activating Token Index: 272

Text #10

Max Range: 6.0196. Min Range: -6.0196

Max Act: 5.7452. Min Act: -0.1700

Data Index: 7995162 (Open Web Text)

Max Activating Token Index: 654

Text #11

Max Range: 6.0196. Min Range: -6.0196

Max Act: 5.7014. Min Act: -0.1700

Data Index: 8791679 (Open Web Text)

Max Activating Token Index: 948

Text #12

Max Range: 6.0196. Min Range: -6.0196

Max Act: 5.7134. Min Act: -0.1700

Data Index: 5145489 (Open Web Text)

Max Activating Token Index: 162

Text #13

Max Range: 6.0196. Min Range: -6.0196

Max Act: 5.7366. Min Act: -0.1700

Data Index: 5523562 (Open Web Text)

Max Activating Token Index: 1021

Text #14

Max Range: 6.0196. Min Range: -6.0196

Max Act: 5.6744. Min Act: -0.1700

Data Index: 5181059 (Open Web Text)

Max Activating Token Index: 281

Text #15

Max Range: 6.0196. Min Range: -6.0196

Max Act: 5.6513. Min Act: -0.1700

Data Index: 7201204 (Open Web Text)

Max Activating Token Index: 983

Text #16

Max Range: 6.0196. Min Range: -6.0196

Max Act: 5.6457. Min Act: -0.1700

Data Index: 6967205 (Open Web Text)

Max Activating Token Index: 973

Text #17

Max Range: 6.0196. Min Range: -6.0196

Max Act: 5.6934. Min Act: -0.1700

Data Index: 7820418 (Open Web Text)

Max Activating Token Index: 369

Text #18

Max Range: 6.0196. Min Range: -6.0196

Max Act: 5.6943. Min Act: -0.1700

Data Index: 8265694 (Open Web Text)

Max Activating Token Index: 1001

Text #19

Max Range: 6.0196. Min Range: -6.0196

Max Act: 5.6569. Min Act: -0.1700

Data Index: 3044439 (Open Web Text)

Max Activating Token Index: 831