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

Dataset: Open Web Text

Neuron 1811 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: 2.7542. Min Range: -2.7542

Max Act: 2.7390. Min Act: -0.1700

Data Index: 1759522 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 2.7542. Min Range: -2.7542

Max Act: 2.7542. Min Act: -0.1700

Data Index: 5492075 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.7542. Min Range: -2.7542

Max Act: 2.7389. Min Act: -0.1700

Data Index: 5502118 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.7542. Min Range: -2.7542

Max Act: 2.7337. Min Act: -0.1700

Data Index: 8420347 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 2.7542. Min Range: -2.7542

Max Act: 2.7169. Min Act: -0.1700

Data Index: 3132366 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.7542. Min Range: -2.7542

Max Act: 2.7221. Min Act: -0.1700

Data Index: 4180522 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.7542. Min Range: -2.7542

Max Act: 2.7186. Min Act: -0.1700

Data Index: 5351067 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 2.7542. Min Range: -2.7542

Max Act: 2.6910. Min Act: -0.1700

Data Index: 1797174 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 2.7542. Min Range: -2.7542

Max Act: 2.6909. Min Act: -0.1700

Data Index: 362178 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 2.7542. Min Range: -2.7542

Max Act: 2.6828. Min Act: -0.1700

Data Index: 909434 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.7542. Min Range: -2.7542

Max Act: 2.6847. Min Act: -0.1700

Data Index: 4880880 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 2.7542. Min Range: -2.7542

Max Act: 2.6552. Min Act: -0.1700

Data Index: 5548216 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.7542. Min Range: -2.7542

Max Act: 2.6482. Min Act: -0.1700

Data Index: 4114064 (Open Web Text)

Max Activating Token Index: 818

Text #13

Max Range: 2.7542. Min Range: -2.7542

Max Act: 2.6563. Min Act: -0.1700

Data Index: 7319067 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 2.7542. Min Range: -2.7542

Max Act: 2.6487. Min Act: -0.1700

Data Index: 3988826 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 2.7542. Min Range: -2.7542

Max Act: 2.6373. Min Act: -0.1700

Data Index: 5316128 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.7542. Min Range: -2.7542

Max Act: 2.6337. Min Act: -0.1700

Data Index: 6337103 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 2.7542. Min Range: -2.7542

Max Act: 2.6381. Min Act: -0.1700

Data Index: 1661657 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 2.7542. Min Range: -2.7542

Max Act: 2.6170. Min Act: -0.1700

Data Index: 5242960 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.7542. Min Range: -2.7542

Max Act: 2.6185. Min Act: -0.1700

Data Index: 1239672 (Open Web Text)

Max Activating Token Index: 2