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

Dataset: Open Web Text

Neuron 573 in Layer 6

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: 4.5249. Min Range: -4.5249

Max Act: 4.5249. Min Act: -0.1700

Data Index: 2830609 (Open Web Text)

Max Activating Token Index: 875

Text #1

Max Range: 4.5249. Min Range: -4.5249

Max Act: 4.5174. Min Act: -0.1700

Data Index: 7598040 (Open Web Text)

Max Activating Token Index: 1016

Text #2

Max Range: 4.5249. Min Range: -4.5249

Max Act: 4.4728. Min Act: -0.1700

Data Index: 107529 (Open Web Text)

Max Activating Token Index: 199

Text #3

Max Range: 4.5249. Min Range: -4.5249

Max Act: 4.4464. Min Act: -0.1700

Data Index: 6269062 (Open Web Text)

Max Activating Token Index: 965

Text #4

Max Range: 4.5249. Min Range: -4.5249

Max Act: 4.4400. Min Act: -0.1700

Data Index: 4099571 (Open Web Text)

Max Activating Token Index: 453

Text #5

Max Range: 4.5249. Min Range: -4.5249

Max Act: 4.4209. Min Act: -0.1700

Data Index: 8146189 (Open Web Text)

Max Activating Token Index: 627

Text #6

Max Range: 4.5249. Min Range: -4.5249

Max Act: 4.3648. Min Act: -0.1700

Data Index: 7426952 (Open Web Text)

Max Activating Token Index: 561

Text #7

Max Range: 4.5249. Min Range: -4.5249

Max Act: 4.3829. Min Act: -0.1700

Data Index: 5793605 (Open Web Text)

Max Activating Token Index: 212

Text #8

Max Range: 4.5249. Min Range: -4.5249

Max Act: 4.3939. Min Act: -0.1700

Data Index: 7426954 (Open Web Text)

Max Activating Token Index: 189

Text #9

Max Range: 4.5249. Min Range: -4.5249

Max Act: 4.3696. Min Act: -0.1700

Data Index: 6415804 (Open Web Text)

Max Activating Token Index: 310

Text #10

Max Range: 4.5249. Min Range: -4.5249

Max Act: 4.3435. Min Act: -0.1700

Data Index: 7243520 (Open Web Text)

Max Activating Token Index: 559

Text #11

Max Range: 4.5249. Min Range: -4.5249

Max Act: 4.3432. Min Act: -0.1700

Data Index: 4481097 (Open Web Text)

Max Activating Token Index: 85

Text #12

Max Range: 4.5249. Min Range: -4.5249

Max Act: 4.3641. Min Act: -0.1700

Data Index: 2146599 (Open Web Text)

Max Activating Token Index: 739

Text #13

Max Range: 4.5249. Min Range: -4.5249

Max Act: 4.3530. Min Act: -0.1700

Data Index: 978877 (Open Web Text)

Max Activating Token Index: 641

Text #14

Max Range: 4.5249. Min Range: -4.5249

Max Act: 4.3328. Min Act: -0.1700

Data Index: 2021281 (Open Web Text)

Max Activating Token Index: 453

Text #15

Max Range: 4.5249. Min Range: -4.5249

Max Act: 4.3441. Min Act: -0.1700

Data Index: 5428060 (Open Web Text)

Max Activating Token Index: 406

Text #16

Max Range: 4.5249. Min Range: -4.5249

Max Act: 4.3089. Min Act: -0.1700

Data Index: 7947707 (Open Web Text)

Max Activating Token Index: 456

Text #17

Max Range: 4.5249. Min Range: -4.5249

Max Act: 4.3142. Min Act: -0.1700

Data Index: 671627 (Open Web Text)

Max Activating Token Index: 1008

Text #18

Max Range: 4.5249. Min Range: -4.5249

Max Act: 4.2445. Min Act: -0.1700

Data Index: 4390876 (Open Web Text)

Max Activating Token Index: 719

Text #19

Max Range: 4.5249. Min Range: -4.5249

Max Act: 4.2196. Min Act: -0.1700

Data Index: 5432985 (Open Web Text)

Max Activating Token Index: 488