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

Dataset: Open Web Text

Neuron 389 in Layer 4

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: 3.4654. Min Range: -3.4654

Max Act: 3.4654. Min Act: -0.1700

Data Index: 4433930 (Open Web Text)

Max Activating Token Index: 602

Text #1

Max Range: 3.4654. Min Range: -3.4654

Max Act: 3.3693. Min Act: -0.1700

Data Index: 4311601 (Open Web Text)

Max Activating Token Index: 123

Text #2

Max Range: 3.4654. Min Range: -3.4654

Max Act: 3.3082. Min Act: -0.1700

Data Index: 5805790 (Open Web Text)

Max Activating Token Index: 853

Text #3

Max Range: 3.4654. Min Range: -3.4654

Max Act: 3.2897. Min Act: -0.1700

Data Index: 6871840 (Open Web Text)

Max Activating Token Index: 970

Text #4

Max Range: 3.4654. Min Range: -3.4654

Max Act: 3.3146. Min Act: -0.1700

Data Index: 4997840 (Open Web Text)

Max Activating Token Index: 716

Text #5

Max Range: 3.4654. Min Range: -3.4654

Max Act: 3.3015. Min Act: -0.1700

Data Index: 2940915 (Open Web Text)

Max Activating Token Index: 550

Text #6

Max Range: 3.4654. Min Range: -3.4654

Max Act: 3.2822. Min Act: -0.1700

Data Index: 2960652 (Open Web Text)

Max Activating Token Index: 353

Text #7

Max Range: 3.4654. Min Range: -3.4654

Max Act: 3.2899. Min Act: -0.1700

Data Index: 8074983 (Open Web Text)

Max Activating Token Index: 417

Text #8

Max Range: 3.4654. Min Range: -3.4654

Max Act: 3.2572. Min Act: -0.1700

Data Index: 1594506 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.4654. Min Range: -3.4654

Max Act: 3.2513. Min Act: -0.1700

Data Index: 3051481 (Open Web Text)

Max Activating Token Index: 32

Text #10

Max Range: 3.4654. Min Range: -3.4654

Max Act: 3.2389. Min Act: -0.1700

Data Index: 832471 (Open Web Text)

Max Activating Token Index: 973

Text #11

Max Range: 3.4654. Min Range: -3.4654

Max Act: 3.2195. Min Act: -0.1700

Data Index: 1758474 (Open Web Text)

Max Activating Token Index: 573

Text #12

Max Range: 3.4654. Min Range: -3.4654

Max Act: 3.2134. Min Act: -0.1700

Data Index: 4458423 (Open Web Text)

Max Activating Token Index: 762

Text #13

Max Range: 3.4654. Min Range: -3.4654

Max Act: 3.2102. Min Act: -0.1700

Data Index: 4687222 (Open Web Text)

Max Activating Token Index: 325

Text #14

Max Range: 3.4654. Min Range: -3.4654

Max Act: 3.2325. Min Act: -0.1700

Data Index: 6425957 (Open Web Text)

Max Activating Token Index: 350

Text #15

Max Range: 3.4654. Min Range: -3.4654

Max Act: 3.1906. Min Act: -0.1700

Data Index: 2112507 (Open Web Text)

Max Activating Token Index: 320

Text #16

Max Range: 3.4654. Min Range: -3.4654

Max Act: 3.2036. Min Act: -0.1700

Data Index: 7500098 (Open Web Text)

Max Activating Token Index: 345

Text #17

Max Range: 3.4654. Min Range: -3.4654

Max Act: 3.1757. Min Act: -0.1700

Data Index: 1026243 (Open Web Text)

Max Activating Token Index: 674

Text #18

Max Range: 3.4654. Min Range: -3.4654

Max Act: 3.2200. Min Act: -0.1700

Data Index: 5398229 (Open Web Text)

Max Activating Token Index: 880

Text #19

Max Range: 3.4654. Min Range: -3.4654

Max Act: 3.1786. Min Act: -0.1700

Data Index: 5622117 (Open Web Text)

Max Activating Token Index: 186