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

Dataset: Open Web Text

Neuron 2918 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: 4.8818. Min Range: -4.8818

Max Act: 4.8818. Min Act: -0.1700

Data Index: 8729715 (Open Web Text)

Max Activating Token Index: 153

Text #1

Max Range: 4.8818. Min Range: -4.8818

Max Act: 4.8327. Min Act: -0.1700

Data Index: 2178950 (Open Web Text)

Max Activating Token Index: 923

Text #2

Max Range: 4.8818. Min Range: -4.8818

Max Act: 4.7503. Min Act: -0.1700

Data Index: 6704831 (Open Web Text)

Max Activating Token Index: 94

Text #3

Max Range: 4.8818. Min Range: -4.8818

Max Act: 4.7539. Min Act: -0.1700

Data Index: 5878277 (Open Web Text)

Max Activating Token Index: 156

Text #4

Max Range: 4.8818. Min Range: -4.8818

Max Act: 4.7627. Min Act: -0.1700

Data Index: 1174645 (Open Web Text)

Max Activating Token Index: 491

Text #5

Max Range: 4.8818. Min Range: -4.8818

Max Act: 4.7850. Min Act: -0.1700

Data Index: 5994275 (Open Web Text)

Max Activating Token Index: 221

Text #6

Max Range: 4.8818. Min Range: -4.8818

Max Act: 4.7224. Min Act: -0.1700

Data Index: 5250618 (Open Web Text)

Max Activating Token Index: 116

Text #7

Max Range: 4.8818. Min Range: -4.8818

Max Act: 4.6719. Min Act: -0.1700

Data Index: 6117374 (Open Web Text)

Max Activating Token Index: 652

Text #8

Max Range: 4.8818. Min Range: -4.8818

Max Act: 4.6080. Min Act: -0.1700

Data Index: 1224806 (Open Web Text)

Max Activating Token Index: 654

Text #9

Max Range: 4.8818. Min Range: -4.8818

Max Act: 4.6351. Min Act: -0.1700

Data Index: 6744299 (Open Web Text)

Max Activating Token Index: 627

Text #10

Max Range: 4.8818. Min Range: -4.8818

Max Act: 4.6265. Min Act: -0.1700

Data Index: 5994278 (Open Web Text)

Max Activating Token Index: 955

Text #11

Max Range: 4.8818. Min Range: -4.8818

Max Act: 4.6061. Min Act: -0.1700

Data Index: 8317913 (Open Web Text)

Max Activating Token Index: 697

Text #12

Max Range: 4.8818. Min Range: -4.8818

Max Act: 4.6673. Min Act: -0.1700

Data Index: 3571554 (Open Web Text)

Max Activating Token Index: 485

Text #13

Max Range: 4.8818. Min Range: -4.8818

Max Act: 4.5983. Min Act: -0.1700

Data Index: 905224 (Open Web Text)

Max Activating Token Index: 828

Text #14

Max Range: 4.8818. Min Range: -4.8818

Max Act: 4.6089. Min Act: -0.1700

Data Index: 524243 (Open Web Text)

Max Activating Token Index: 99

Text #15

Max Range: 4.8818. Min Range: -4.8818

Max Act: 4.6001. Min Act: -0.1700

Data Index: 1784285 (Open Web Text)

Max Activating Token Index: 702

Text #16

Max Range: 4.8818. Min Range: -4.8818

Max Act: 4.6288. Min Act: -0.1700

Data Index: 3227820 (Open Web Text)

Max Activating Token Index: 77

Text #17

Max Range: 4.8818. Min Range: -4.8818

Max Act: 4.6037. Min Act: -0.1700

Data Index: 4673486 (Open Web Text)

Max Activating Token Index: 1021

Text #18

Max Range: 4.8818. Min Range: -4.8818

Max Act: 4.5444. Min Act: -0.1700

Data Index: 1966264 (Open Web Text)

Max Activating Token Index: 618

Text #19

Max Range: 4.8818. Min Range: -4.8818

Max Act: 4.5670. Min Act: -0.1700

Data Index: 5250405 (Open Web Text)

Max Activating Token Index: 480