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

Dataset: Open Web Text

Neuron 765 in Layer 0

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: 2.7956. Min Range: -2.7956

Max Act: 2.7904. Min Act: -0.1700

Data Index: 8746959 (Open Web Text)

Max Activating Token Index: 21

Text #1

Max Range: 2.7956. Min Range: -2.7956

Max Act: 2.7956. Min Act: -0.1700

Data Index: 3146314 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 2.7956. Min Range: -2.7956

Max Act: 2.7708. Min Act: -0.1700

Data Index: 1106475 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 2.7956. Min Range: -2.7956

Max Act: 2.7500. Min Act: -0.1700

Data Index: 8826581 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.7956. Min Range: -2.7956

Max Act: 2.7512. Min Act: -0.1700

Data Index: 2197024 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 2.7956. Min Range: -2.7956

Max Act: 2.7484. Min Act: -0.1700

Data Index: 5550669 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 2.7956. Min Range: -2.7956

Max Act: 2.7511. Min Act: -0.1700

Data Index: 420815 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 2.7956. Min Range: -2.7956

Max Act: 2.7314. Min Act: -0.1700

Data Index: 255254 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.7956. Min Range: -2.7956

Max Act: 2.7233. Min Act: -0.1700

Data Index: 5894694 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 2.7956. Min Range: -2.7956

Max Act: 2.7429. Min Act: -0.1700

Data Index: 6366541 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.7956. Min Range: -2.7956

Max Act: 2.7306. Min Act: -0.1700

Data Index: 8816463 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 2.7956. Min Range: -2.7956

Max Act: 2.7114. Min Act: -0.1700

Data Index: 7677282 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.7956. Min Range: -2.7956

Max Act: 2.7132. Min Act: -0.1700

Data Index: 6972509 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 2.7956. Min Range: -2.7956

Max Act: 2.7038. Min Act: -0.1700

Data Index: 2203422 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 2.7956. Min Range: -2.7956

Max Act: 2.7192. Min Act: -0.1700

Data Index: 5018398 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 2.7956. Min Range: -2.7956

Max Act: 2.7020. Min Act: -0.1700

Data Index: 1898914 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 2.7956. Min Range: -2.7956

Max Act: 2.6923. Min Act: -0.1700

Data Index: 220627 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.7956. Min Range: -2.7956

Max Act: 2.6911. Min Act: -0.1700

Data Index: 1962793 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 2.7956. Min Range: -2.7956

Max Act: 2.6927. Min Act: -0.1700

Data Index: 6525182 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 2.7956. Min Range: -2.7956

Max Act: 2.7008. Min Act: -0.1700

Data Index: 7348363 (Open Web Text)

Max Activating Token Index: 5