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

Dataset: Open Web Text

Neuron 3066 in Layer 3

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: 3.6554. Min Range: -3.6554

Max Act: 3.6554. Min Act: -0.1700

Data Index: 5227369 (Open Web Text)

Max Activating Token Index: 100

Text #1

Max Range: 3.6554. Min Range: -3.6554

Max Act: 3.6192. Min Act: -0.1700

Data Index: 2268554 (Open Web Text)

Max Activating Token Index: 179

Text #2

Max Range: 3.6554. Min Range: -3.6554

Max Act: 3.5942. Min Act: -0.1700

Data Index: 6476183 (Open Web Text)

Max Activating Token Index: 591

Text #3

Max Range: 3.6554. Min Range: -3.6554

Max Act: 3.6260. Min Act: -0.1700

Data Index: 8534292 (Open Web Text)

Max Activating Token Index: 420

Text #4

Max Range: 3.6554. Min Range: -3.6554

Max Act: 3.6035. Min Act: -0.1700

Data Index: 7842819 (Open Web Text)

Max Activating Token Index: 850

Text #5

Max Range: 3.6554. Min Range: -3.6554

Max Act: 3.6360. Min Act: -0.1700

Data Index: 2300389 (Open Web Text)

Max Activating Token Index: 130

Text #6

Max Range: 3.6554. Min Range: -3.6554

Max Act: 3.6341. Min Act: -0.1700

Data Index: 223013 (Open Web Text)

Max Activating Token Index: 594

Text #7

Max Range: 3.6554. Min Range: -3.6554

Max Act: 3.6189. Min Act: -0.1700

Data Index: 7914467 (Open Web Text)

Max Activating Token Index: 914

Text #8

Max Range: 3.6554. Min Range: -3.6554

Max Act: 3.6436. Min Act: -0.1700

Data Index: 202167 (Open Web Text)

Max Activating Token Index: 933

Text #9

Max Range: 3.6554. Min Range: -3.6554

Max Act: 3.6034. Min Act: -0.1700

Data Index: 2968026 (Open Web Text)

Max Activating Token Index: 785

Text #10

Max Range: 3.6554. Min Range: -3.6554

Max Act: 3.6050. Min Act: -0.1700

Data Index: 953688 (Open Web Text)

Max Activating Token Index: 631

Text #11

Max Range: 3.6554. Min Range: -3.6554

Max Act: 3.5930. Min Act: -0.1700

Data Index: 3627948 (Open Web Text)

Max Activating Token Index: 992

Text #12

Max Range: 3.6554. Min Range: -3.6554

Max Act: 3.5748. Min Act: -0.1700

Data Index: 549032 (Open Web Text)

Max Activating Token Index: 944

Text #13

Max Range: 3.6554. Min Range: -3.6554

Max Act: 3.5726. Min Act: -0.1700

Data Index: 4863178 (Open Web Text)

Max Activating Token Index: 765

Text #14

Max Range: 3.6554. Min Range: -3.6554

Max Act: 3.5531. Min Act: -0.1700

Data Index: 7790310 (Open Web Text)

Max Activating Token Index: 73

Text #15

Max Range: 3.6554. Min Range: -3.6554

Max Act: 3.5520. Min Act: -0.1700

Data Index: 7581601 (Open Web Text)

Max Activating Token Index: 51

Text #16

Max Range: 3.6554. Min Range: -3.6554

Max Act: 3.5248. Min Act: -0.1700

Data Index: 8129971 (Open Web Text)

Max Activating Token Index: 424

Text #17

Max Range: 3.6554. Min Range: -3.6554

Max Act: 3.5867. Min Act: -0.1700

Data Index: 6798410 (Open Web Text)

Max Activating Token Index: 1002

Text #18

Max Range: 3.6554. Min Range: -3.6554

Max Act: 3.5688. Min Act: -0.1700

Data Index: 4283232 (Open Web Text)

Max Activating Token Index: 330

Text #19

Max Range: 3.6554. Min Range: -3.6554

Max Act: 3.5434. Min Act: -0.1700

Data Index: 1139390 (Open Web Text)

Max Activating Token Index: 536