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

Dataset: Open Web Text

Neuron 507 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: 3.9614. Min Range: -3.9614

Max Act: 3.9614. Min Act: -0.1700

Data Index: 3240711 (Open Web Text)

Max Activating Token Index: 496

Text #1

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.9221. Min Act: -0.1700

Data Index: 2568291 (Open Web Text)

Max Activating Token Index: 211

Text #2

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.8215. Min Act: -0.1700

Data Index: 6784033 (Open Web Text)

Max Activating Token Index: 684

Text #3

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.8238. Min Act: -0.1700

Data Index: 191162 (Open Web Text)

Max Activating Token Index: 754

Text #4

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.8007. Min Act: -0.1700

Data Index: 2337633 (Open Web Text)

Max Activating Token Index: 527

Text #5

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.7860. Min Act: -0.1700

Data Index: 5046731 (Open Web Text)

Max Activating Token Index: 793

Text #6

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.7933. Min Act: -0.1700

Data Index: 6272174 (Open Web Text)

Max Activating Token Index: 979

Text #7

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.7507. Min Act: -0.1700

Data Index: 1583759 (Open Web Text)

Max Activating Token Index: 659

Text #8

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.7445. Min Act: -0.1700

Data Index: 8776514 (Open Web Text)

Max Activating Token Index: 754

Text #9

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.7167. Min Act: -0.1700

Data Index: 857469 (Open Web Text)

Max Activating Token Index: 268

Text #10

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.7047. Min Act: -0.1700

Data Index: 4499180 (Open Web Text)

Max Activating Token Index: 119

Text #11

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.7054. Min Act: -0.1700

Data Index: 794663 (Open Web Text)

Max Activating Token Index: 866

Text #12

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.7186. Min Act: -0.1700

Data Index: 1212975 (Open Web Text)

Max Activating Token Index: 313

Text #13

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.7025. Min Act: -0.1700

Data Index: 2358904 (Open Web Text)

Max Activating Token Index: 155

Text #14

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.6888. Min Act: -0.1700

Data Index: 5411426 (Open Web Text)

Max Activating Token Index: 15

Text #15

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.6630. Min Act: -0.1700

Data Index: 4243401 (Open Web Text)

Max Activating Token Index: 953

Text #16

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.6548. Min Act: -0.1700

Data Index: 168982 (Open Web Text)

Max Activating Token Index: 856

Text #17

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.6660. Min Act: -0.1700

Data Index: 6579443 (Open Web Text)

Max Activating Token Index: 206

Text #18

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.6707. Min Act: -0.1700

Data Index: 1970405 (Open Web Text)

Max Activating Token Index: 872

Text #19

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.6482. Min Act: -0.1700

Data Index: 3497271 (Open Web Text)

Max Activating Token Index: 197