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

Dataset: Open Web Text

Neuron 2369 in Layer 2

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: 1.5929. Min Range: -1.5929

Max Act: 1.5929. Min Act: -0.1700

Data Index: 7910347 (Open Web Text)

Max Activating Token Index: 365

Text #1

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.5882. Min Act: -0.1700

Data Index: 3006385 (Open Web Text)

Max Activating Token Index: 623

Text #2

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.5764. Min Act: -0.1668

Data Index: 7810504 (Open Web Text)

Max Activating Token Index: 706

Text #3

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.5664. Min Act: -0.1700

Data Index: 8296322 (Open Web Text)

Max Activating Token Index: 341

Text #4

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.5637. Min Act: -0.1700

Data Index: 2212222 (Open Web Text)

Max Activating Token Index: 814

Text #5

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.5623. Min Act: -0.1700

Data Index: 1094667 (Open Web Text)

Max Activating Token Index: 789

Text #6

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.5512. Min Act: -0.1700

Data Index: 4461582 (Open Web Text)

Max Activating Token Index: 235

Text #7

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.5487. Min Act: -0.1699

Data Index: 1574246 (Open Web Text)

Max Activating Token Index: 431

Text #8

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.5236. Min Act: -0.1700

Data Index: 3006388 (Open Web Text)

Max Activating Token Index: 333

Text #9

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.5265. Min Act: -0.1700

Data Index: 1915721 (Open Web Text)

Max Activating Token Index: 542

Text #10

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.5107. Min Act: -0.1700

Data Index: 6984775 (Open Web Text)

Max Activating Token Index: 126

Text #11

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.5094. Min Act: -0.1700

Data Index: 2205316 (Open Web Text)

Max Activating Token Index: 521

Text #12

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.5140. Min Act: -0.1700

Data Index: 1156283 (Open Web Text)

Max Activating Token Index: 361

Text #13

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.5140. Min Act: -0.1700

Data Index: 5093432 (Open Web Text)

Max Activating Token Index: 798

Text #14

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.5076. Min Act: -0.1699

Data Index: 387867 (Open Web Text)

Max Activating Token Index: 114

Text #15

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.5056. Min Act: -0.1697

Data Index: 3999766 (Open Web Text)

Max Activating Token Index: 424

Text #16

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.5075. Min Act: -0.1700

Data Index: 6934018 (Open Web Text)

Max Activating Token Index: 655

Text #17

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.5135. Min Act: -0.1700

Data Index: 2567929 (Open Web Text)

Max Activating Token Index: 639

Text #18

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.4995. Min Act: -0.1700

Data Index: 738660 (Open Web Text)

Max Activating Token Index: 357

Text #19

Max Range: 1.5929. Min Range: -1.5929

Max Act: 1.4970. Min Act: -0.1696

Data Index: 2640120 (Open Web Text)

Max Activating Token Index: 444