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

Dataset: Open Web Text

Neuron 378 in Layer 4

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: 4.2505. Min Range: -4.2505

Max Act: 4.2135. Min Act: -0.1700

Data Index: 3741485 (Open Web Text)

Max Activating Token Index: 598

Text #1

Max Range: 4.2505. Min Range: -4.2505

Max Act: 4.2505. Min Act: -0.1700

Data Index: 5858560 (Open Web Text)

Max Activating Token Index: 827

Text #2

Max Range: 4.2505. Min Range: -4.2505

Max Act: 4.1756. Min Act: -0.1700

Data Index: 866514 (Open Web Text)

Max Activating Token Index: 858

Text #3

Max Range: 4.2505. Min Range: -4.2505

Max Act: 4.1421. Min Act: -0.1700

Data Index: 4263434 (Open Web Text)

Max Activating Token Index: 858

Text #4

Max Range: 4.2505. Min Range: -4.2505

Max Act: 4.1023. Min Act: -0.1700

Data Index: 2028958 (Open Web Text)

Max Activating Token Index: 94

Text #5

Max Range: 4.2505. Min Range: -4.2505

Max Act: 4.0757. Min Act: -0.1700

Data Index: 5874692 (Open Web Text)

Max Activating Token Index: 401

Text #6

Max Range: 4.2505. Min Range: -4.2505

Max Act: 4.0947. Min Act: -0.1700

Data Index: 1109788 (Open Web Text)

Max Activating Token Index: 184

Text #7

Max Range: 4.2505. Min Range: -4.2505

Max Act: 4.0719. Min Act: -0.1700

Data Index: 7331360 (Open Web Text)

Max Activating Token Index: 816

Text #8

Max Range: 4.2505. Min Range: -4.2505

Max Act: 4.0786. Min Act: -0.1700

Data Index: 6679212 (Open Web Text)

Max Activating Token Index: 423

Text #9

Max Range: 4.2505. Min Range: -4.2505

Max Act: 4.0349. Min Act: -0.1700

Data Index: 784203 (Open Web Text)

Max Activating Token Index: 644

Text #10

Max Range: 4.2505. Min Range: -4.2505

Max Act: 4.0641. Min Act: -0.1700

Data Index: 1446301 (Open Web Text)

Max Activating Token Index: 908

Text #11

Max Range: 4.2505. Min Range: -4.2505

Max Act: 4.0702. Min Act: -0.1700

Data Index: 6136302 (Open Web Text)

Max Activating Token Index: 680

Text #12

Max Range: 4.2505. Min Range: -4.2505

Max Act: 4.0445. Min Act: -0.1700

Data Index: 3987086 (Open Web Text)

Max Activating Token Index: 135

Text #13

Max Range: 4.2505. Min Range: -4.2505

Max Act: 4.0672. Min Act: -0.1700

Data Index: 8071247 (Open Web Text)

Max Activating Token Index: 998

Text #14

Max Range: 4.2505. Min Range: -4.2505

Max Act: 4.0236. Min Act: -0.1700

Data Index: 7414592 (Open Web Text)

Max Activating Token Index: 25

Text #15

Max Range: 4.2505. Min Range: -4.2505

Max Act: 4.0170. Min Act: -0.1700

Data Index: 4196795 (Open Web Text)

Max Activating Token Index: 896

Text #16

Max Range: 4.2505. Min Range: -4.2505

Max Act: 4.0086. Min Act: -0.1700

Data Index: 1189662 (Open Web Text)

Max Activating Token Index: 847

Text #17

Max Range: 4.2505. Min Range: -4.2505

Max Act: 4.0139. Min Act: -0.1700

Data Index: 6584313 (Open Web Text)

Max Activating Token Index: 630

Text #18

Max Range: 4.2505. Min Range: -4.2505

Max Act: 3.9977. Min Act: -0.1700

Data Index: 7251137 (Open Web Text)

Max Activating Token Index: 321

Text #19

Max Range: 4.2505. Min Range: -4.2505

Max Act: 4.0342. Min Act: -0.1700

Data Index: 633565 (Open Web Text)

Max Activating Token Index: 952