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

Dataset: Open Web Text

Neuron 454 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: 4.6943. Min Range: -4.6943

Max Act: 4.6943. Min Act: -0.1700

Data Index: 8826911 (Open Web Text)

Max Activating Token Index: 1004

Text #1

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.5509. Min Act: -0.1700

Data Index: 4320240 (Open Web Text)

Max Activating Token Index: 335

Text #2

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.5529. Min Act: -0.1700

Data Index: 2505749 (Open Web Text)

Max Activating Token Index: 852

Text #3

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.5887. Min Act: -0.1700

Data Index: 7938395 (Open Web Text)

Max Activating Token Index: 702

Text #4

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.4903. Min Act: -0.1700

Data Index: 1847240 (Open Web Text)

Max Activating Token Index: 300

Text #5

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.5209. Min Act: -0.1700

Data Index: 305920 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.4783. Min Act: -0.1700

Data Index: 2881282 (Open Web Text)

Max Activating Token Index: 136

Text #7

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.4639. Min Act: -0.1700

Data Index: 4171072 (Open Web Text)

Max Activating Token Index: 572

Text #8

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.4714. Min Act: -0.1700

Data Index: 2162812 (Open Web Text)

Max Activating Token Index: 274

Text #9

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.4152. Min Act: -0.1700

Data Index: 6977737 (Open Web Text)

Max Activating Token Index: 735

Text #10

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.4574. Min Act: -0.1700

Data Index: 8021671 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.4115. Min Act: -0.1700

Data Index: 8762803 (Open Web Text)

Max Activating Token Index: 805

Text #12

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.4053. Min Act: -0.1700

Data Index: 3788002 (Open Web Text)

Max Activating Token Index: 903

Text #13

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.4222. Min Act: -0.1700

Data Index: 4651901 (Open Web Text)

Max Activating Token Index: 230

Text #14

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.4344. Min Act: -0.1700

Data Index: 5388893 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.4084. Min Act: -0.1700

Data Index: 2077580 (Open Web Text)

Max Activating Token Index: 267

Text #16

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.3595. Min Act: -0.1700

Data Index: 4012222 (Open Web Text)

Max Activating Token Index: 400

Text #17

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.3940. Min Act: -0.1700

Data Index: 4368711 (Open Web Text)

Max Activating Token Index: 552

Text #18

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.3768. Min Act: -0.1700

Data Index: 1802490 (Open Web Text)

Max Activating Token Index: 133

Text #19

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.3998. Min Act: -0.1700

Data Index: 8521388 (Open Web Text)

Max Activating Token Index: 780