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

Dataset: Open Web Text

Neuron 2364 in Layer 5

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: 3.8157. Min Range: -3.8157

Max Act: 3.8157. Min Act: -0.1700

Data Index: 328809 (Open Web Text)

Max Activating Token Index: 259

Text #1

Max Range: 3.8157. Min Range: -3.8157

Max Act: 3.7665. Min Act: -0.1700

Data Index: 440449 (Open Web Text)

Max Activating Token Index: 140

Text #2

Max Range: 3.8157. Min Range: -3.8157

Max Act: 3.7726. Min Act: -0.1700

Data Index: 8083741 (Open Web Text)

Max Activating Token Index: 56

Text #3

Max Range: 3.8157. Min Range: -3.8157

Max Act: 3.7533. Min Act: -0.1700

Data Index: 8393723 (Open Web Text)

Max Activating Token Index: 687

Text #4

Max Range: 3.8157. Min Range: -3.8157

Max Act: 3.7661. Min Act: -0.1700

Data Index: 3557972 (Open Web Text)

Max Activating Token Index: 894

Text #5

Max Range: 3.8157. Min Range: -3.8157

Max Act: 3.7071. Min Act: -0.1700

Data Index: 1514935 (Open Web Text)

Max Activating Token Index: 279

Text #6

Max Range: 3.8157. Min Range: -3.8157

Max Act: 3.7025. Min Act: -0.1700

Data Index: 4857026 (Open Web Text)

Max Activating Token Index: 469

Text #7

Max Range: 3.8157. Min Range: -3.8157

Max Act: 3.6950. Min Act: -0.1700

Data Index: 6379897 (Open Web Text)

Max Activating Token Index: 713

Text #8

Max Range: 3.8157. Min Range: -3.8157

Max Act: 3.7512. Min Act: -0.1700

Data Index: 7506795 (Open Web Text)

Max Activating Token Index: 988

Text #9

Max Range: 3.8157. Min Range: -3.8157

Max Act: 3.6858. Min Act: -0.1700

Data Index: 6379422 (Open Web Text)

Max Activating Token Index: 462

Text #10

Max Range: 3.8157. Min Range: -3.8157

Max Act: 3.7111. Min Act: -0.1700

Data Index: 4115019 (Open Web Text)

Max Activating Token Index: 254

Text #11

Max Range: 3.8157. Min Range: -3.8157

Max Act: 3.6653. Min Act: -0.1700

Data Index: 2674857 (Open Web Text)

Max Activating Token Index: 749

Text #12

Max Range: 3.8157. Min Range: -3.8157

Max Act: 3.6774. Min Act: -0.1700

Data Index: 6540444 (Open Web Text)

Max Activating Token Index: 408

Text #13

Max Range: 3.8157. Min Range: -3.8157

Max Act: 3.6444. Min Act: -0.1700

Data Index: 5316877 (Open Web Text)

Max Activating Token Index: 819

Text #14

Max Range: 3.8157. Min Range: -3.8157

Max Act: 3.6453. Min Act: -0.1700

Data Index: 8642862 (Open Web Text)

Max Activating Token Index: 32

Text #15

Max Range: 3.8157. Min Range: -3.8157

Max Act: 3.6520. Min Act: -0.1700

Data Index: 7860561 (Open Web Text)

Max Activating Token Index: 301

Text #16

Max Range: 3.8157. Min Range: -3.8157

Max Act: 3.6044. Min Act: -0.1700

Data Index: 5023180 (Open Web Text)

Max Activating Token Index: 150

Text #17

Max Range: 3.8157. Min Range: -3.8157

Max Act: 3.6260. Min Act: -0.1700

Data Index: 923485 (Open Web Text)

Max Activating Token Index: 701

Text #18

Max Range: 3.8157. Min Range: -3.8157

Max Act: 3.6215. Min Act: -0.1700

Data Index: 7215167 (Open Web Text)

Max Activating Token Index: 785

Text #19

Max Range: 3.8157. Min Range: -3.8157

Max Act: 3.5896. Min Act: -0.1700

Data Index: 8264142 (Open Web Text)

Max Activating Token Index: 325