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

Dataset: Open Web Text

Neuron 648 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: 3.2205. Min Range: -3.2205

Max Act: 3.2205. Min Act: -0.1700

Data Index: 1028854 (Open Web Text)

Max Activating Token Index: 164

Text #1

Max Range: 3.2205. Min Range: -3.2205

Max Act: 3.0664. Min Act: -0.1700

Data Index: 7871252 (Open Web Text)

Max Activating Token Index: 754

Text #2

Max Range: 3.2205. Min Range: -3.2205

Max Act: 3.1396. Min Act: -0.1700

Data Index: 1971527 (Open Web Text)

Max Activating Token Index: 430

Text #3

Max Range: 3.2205. Min Range: -3.2205

Max Act: 3.1550. Min Act: -0.1700

Data Index: 1185239 (Open Web Text)

Max Activating Token Index: 777

Text #4

Max Range: 3.2205. Min Range: -3.2205

Max Act: 3.1340. Min Act: -0.1700

Data Index: 7355778 (Open Web Text)

Max Activating Token Index: 175

Text #5

Max Range: 3.2205. Min Range: -3.2205

Max Act: 3.0429. Min Act: -0.1700

Data Index: 6822489 (Open Web Text)

Max Activating Token Index: 462

Text #6

Max Range: 3.2205. Min Range: -3.2205

Max Act: 3.0504. Min Act: -0.1700

Data Index: 4452245 (Open Web Text)

Max Activating Token Index: 667

Text #7

Max Range: 3.2205. Min Range: -3.2205

Max Act: 3.0390. Min Act: -0.1700

Data Index: 5098239 (Open Web Text)

Max Activating Token Index: 423

Text #8

Max Range: 3.2205. Min Range: -3.2205

Max Act: 2.9836. Min Act: -0.1700

Data Index: 6346158 (Open Web Text)

Max Activating Token Index: 440

Text #9

Max Range: 3.2205. Min Range: -3.2205

Max Act: 2.9908. Min Act: -0.1700

Data Index: 1028843 (Open Web Text)

Max Activating Token Index: 192

Text #10

Max Range: 3.2205. Min Range: -3.2205

Max Act: 3.0338. Min Act: -0.1700

Data Index: 1247687 (Open Web Text)

Max Activating Token Index: 916

Text #11

Max Range: 3.2205. Min Range: -3.2205

Max Act: 3.0001. Min Act: -0.1700

Data Index: 6960039 (Open Web Text)

Max Activating Token Index: 151

Text #12

Max Range: 3.2205. Min Range: -3.2205

Max Act: 2.9838. Min Act: -0.1700

Data Index: 5554949 (Open Web Text)

Max Activating Token Index: 532

Text #13

Max Range: 3.2205. Min Range: -3.2205

Max Act: 2.9701. Min Act: -0.1700

Data Index: 1247697 (Open Web Text)

Max Activating Token Index: 336

Text #14

Max Range: 3.2205. Min Range: -3.2205

Max Act: 2.9768. Min Act: -0.1700

Data Index: 8396669 (Open Web Text)

Max Activating Token Index: 130

Text #15

Max Range: 3.2205. Min Range: -3.2205

Max Act: 2.9566. Min Act: -0.1700

Data Index: 7871253 (Open Web Text)

Max Activating Token Index: 249

Text #16

Max Range: 3.2205. Min Range: -3.2205

Max Act: 2.9714. Min Act: -0.1700

Data Index: 4313726 (Open Web Text)

Max Activating Token Index: 741

Text #17

Max Range: 3.2205. Min Range: -3.2205

Max Act: 2.9684. Min Act: -0.1700

Data Index: 1595674 (Open Web Text)

Max Activating Token Index: 100

Text #18

Max Range: 3.2205. Min Range: -3.2205

Max Act: 2.9657. Min Act: -0.1700

Data Index: 6006143 (Open Web Text)

Max Activating Token Index: 290

Text #19

Max Range: 3.2205. Min Range: -3.2205

Max Act: 2.9733. Min Act: -0.1700

Data Index: 5287595 (Open Web Text)

Max Activating Token Index: 965