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

Dataset: Open Web Text

Neuron 2627 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: 4.1768. Min Range: -4.1768

Max Act: 4.1768. Min Act: -0.1700

Data Index: 6233775 (Open Web Text)

Max Activating Token Index: 300

Text #1

Max Range: 4.1768. Min Range: -4.1768

Max Act: 4.0938. Min Act: -0.1700

Data Index: 1124331 (Open Web Text)

Max Activating Token Index: 834

Text #2

Max Range: 4.1768. Min Range: -4.1768

Max Act: 4.0280. Min Act: -0.1700

Data Index: 1507456 (Open Web Text)

Max Activating Token Index: 398

Text #3

Max Range: 4.1768. Min Range: -4.1768

Max Act: 4.0041. Min Act: -0.1700

Data Index: 5601468 (Open Web Text)

Max Activating Token Index: 56

Text #4

Max Range: 4.1768. Min Range: -4.1768

Max Act: 3.8879. Min Act: -0.1700

Data Index: 3051881 (Open Web Text)

Max Activating Token Index: 683

Text #5

Max Range: 4.1768. Min Range: -4.1768

Max Act: 3.8649. Min Act: -0.1700

Data Index: 459989 (Open Web Text)

Max Activating Token Index: 36

Text #6

Max Range: 4.1768. Min Range: -4.1768

Max Act: 3.8588. Min Act: -0.1700

Data Index: 5524742 (Open Web Text)

Max Activating Token Index: 421

Text #7

Max Range: 4.1768. Min Range: -4.1768

Max Act: 3.8455. Min Act: -0.1700

Data Index: 5221171 (Open Web Text)

Max Activating Token Index: 73

Text #8

Max Range: 4.1768. Min Range: -4.1768

Max Act: 3.8567. Min Act: -0.1700

Data Index: 5010536 (Open Web Text)

Max Activating Token Index: 971

Text #9

Max Range: 4.1768. Min Range: -4.1768

Max Act: 3.8279. Min Act: -0.1700

Data Index: 3243100 (Open Web Text)

Max Activating Token Index: 654

Text #10

Max Range: 4.1768. Min Range: -4.1768

Max Act: 3.7918. Min Act: -0.1700

Data Index: 5749282 (Open Web Text)

Max Activating Token Index: 136

Text #11

Max Range: 4.1768. Min Range: -4.1768

Max Act: 3.8096. Min Act: -0.1700

Data Index: 6584297 (Open Web Text)

Max Activating Token Index: 70

Text #12

Max Range: 4.1768. Min Range: -4.1768

Max Act: 3.7790. Min Act: -0.1700

Data Index: 3937617 (Open Web Text)

Max Activating Token Index: 561

Text #13

Max Range: 4.1768. Min Range: -4.1768

Max Act: 3.7809. Min Act: -0.1700

Data Index: 1293003 (Open Web Text)

Max Activating Token Index: 228

Text #14

Max Range: 4.1768. Min Range: -4.1768

Max Act: 3.7854. Min Act: -0.1700

Data Index: 4093645 (Open Web Text)

Max Activating Token Index: 107

Text #15

Max Range: 4.1768. Min Range: -4.1768

Max Act: 3.7676. Min Act: -0.1700

Data Index: 7290595 (Open Web Text)

Max Activating Token Index: 58

Text #16

Max Range: 4.1768. Min Range: -4.1768

Max Act: 3.7468. Min Act: -0.1700

Data Index: 3115875 (Open Web Text)

Max Activating Token Index: 867

Text #17

Max Range: 4.1768. Min Range: -4.1768

Max Act: 3.7768. Min Act: -0.1700

Data Index: 1124333 (Open Web Text)

Max Activating Token Index: 882

Text #18

Max Range: 4.1768. Min Range: -4.1768

Max Act: 3.7761. Min Act: -0.1700

Data Index: 2022711 (Open Web Text)

Max Activating Token Index: 342

Text #19

Max Range: 4.1768. Min Range: -4.1768

Max Act: 3.7457. Min Act: -0.1700

Data Index: 2273981 (Open Web Text)

Max Activating Token Index: 143