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

Dataset: Open Web Text

Neuron 2410 in Layer 2

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: 4.7056. Min Range: -4.7056

Max Act: 4.7056. Min Act: -0.1700

Data Index: 3907301 (Open Web Text)

Max Activating Token Index: 1009

Text #1

Max Range: 4.7056. Min Range: -4.7056

Max Act: 4.6466. Min Act: -0.1700

Data Index: 638411 (Open Web Text)

Max Activating Token Index: 67

Text #2

Max Range: 4.7056. Min Range: -4.7056

Max Act: 4.6093. Min Act: -0.1700

Data Index: 6939976 (Open Web Text)

Max Activating Token Index: 980

Text #3

Max Range: 4.7056. Min Range: -4.7056

Max Act: 4.6279. Min Act: -0.1700

Data Index: 1731115 (Open Web Text)

Max Activating Token Index: 681

Text #4

Max Range: 4.7056. Min Range: -4.7056

Max Act: 4.5723. Min Act: -0.1700

Data Index: 4713242 (Open Web Text)

Max Activating Token Index: 379

Text #5

Max Range: 4.7056. Min Range: -4.7056

Max Act: 4.6167. Min Act: -0.1700

Data Index: 5558587 (Open Web Text)

Max Activating Token Index: 717

Text #6

Max Range: 4.7056. Min Range: -4.7056

Max Act: 4.5912. Min Act: -0.1700

Data Index: 321352 (Open Web Text)

Max Activating Token Index: 615

Text #7

Max Range: 4.7056. Min Range: -4.7056

Max Act: 4.6052. Min Act: -0.1700

Data Index: 1145303 (Open Web Text)

Max Activating Token Index: 568

Text #8

Max Range: 4.7056. Min Range: -4.7056

Max Act: 4.5587. Min Act: -0.1700

Data Index: 240297 (Open Web Text)

Max Activating Token Index: 954

Text #9

Max Range: 4.7056. Min Range: -4.7056

Max Act: 4.5572. Min Act: -0.1700

Data Index: 4460614 (Open Web Text)

Max Activating Token Index: 991

Text #10

Max Range: 4.7056. Min Range: -4.7056

Max Act: 4.5599. Min Act: -0.1700

Data Index: 3907310 (Open Web Text)

Max Activating Token Index: 216

Text #11

Max Range: 4.7056. Min Range: -4.7056

Max Act: 4.5245. Min Act: -0.1700

Data Index: 588643 (Open Web Text)

Max Activating Token Index: 601

Text #12

Max Range: 4.7056. Min Range: -4.7056

Max Act: 4.4984. Min Act: -0.1700

Data Index: 2686323 (Open Web Text)

Max Activating Token Index: 1000

Text #13

Max Range: 4.7056. Min Range: -4.7056

Max Act: 4.5212. Min Act: -0.1700

Data Index: 4425267 (Open Web Text)

Max Activating Token Index: 642

Text #14

Max Range: 4.7056. Min Range: -4.7056

Max Act: 4.5314. Min Act: -0.1700

Data Index: 6574631 (Open Web Text)

Max Activating Token Index: 848

Text #15

Max Range: 4.7056. Min Range: -4.7056

Max Act: 4.5444. Min Act: -0.1700

Data Index: 4168656 (Open Web Text)

Max Activating Token Index: 654

Text #16

Max Range: 4.7056. Min Range: -4.7056

Max Act: 4.5328. Min Act: -0.1700

Data Index: 4157747 (Open Web Text)

Max Activating Token Index: 132

Text #17

Max Range: 4.7056. Min Range: -4.7056

Max Act: 4.5543. Min Act: -0.1700

Data Index: 137569 (Open Web Text)

Max Activating Token Index: 640

Text #18

Max Range: 4.7056. Min Range: -4.7056

Max Act: 4.4996. Min Act: -0.1700

Data Index: 1862645 (Open Web Text)

Max Activating Token Index: 64

Text #19

Max Range: 4.7056. Min Range: -4.7056

Max Act: 4.4818. Min Act: -0.1700

Data Index: 2149429 (Open Web Text)

Max Activating Token Index: 124