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

Dataset: Open Web Text

Neuron 2683 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: 1.9207. Min Range: -1.9207

Max Act: 1.9207. Min Act: -0.1691

Data Index: 3715918 (Open Web Text)

Max Activating Token Index: 391

Text #1

Max Range: 1.9207. Min Range: -1.9207

Max Act: 1.8481. Min Act: -0.1700

Data Index: 8288015 (Open Web Text)

Max Activating Token Index: 595

Text #2

Max Range: 1.9207. Min Range: -1.9207

Max Act: 1.8309. Min Act: -0.1700

Data Index: 8287998 (Open Web Text)

Max Activating Token Index: 496

Text #3

Max Range: 1.9207. Min Range: -1.9207

Max Act: 1.8348. Min Act: -0.1700

Data Index: 5325228 (Open Web Text)

Max Activating Token Index: 455

Text #4

Max Range: 1.9207. Min Range: -1.9207

Max Act: 1.8295. Min Act: -0.1700

Data Index: 4771541 (Open Web Text)

Max Activating Token Index: 306

Text #5

Max Range: 1.9207. Min Range: -1.9207

Max Act: 1.7985. Min Act: -0.1700

Data Index: 1593606 (Open Web Text)

Max Activating Token Index: 634

Text #6

Max Range: 1.9207. Min Range: -1.9207

Max Act: 1.7950. Min Act: -0.1700

Data Index: 189692 (Open Web Text)

Max Activating Token Index: 588

Text #7

Max Range: 1.9207. Min Range: -1.9207

Max Act: 1.7811. Min Act: -0.1678

Data Index: 1063442 (Open Web Text)

Max Activating Token Index: 313

Text #8

Max Range: 1.9207. Min Range: -1.9207

Max Act: 1.7823. Min Act: -0.1700

Data Index: 6952165 (Open Web Text)

Max Activating Token Index: 447

Text #9

Max Range: 1.9207. Min Range: -1.9207

Max Act: 1.7712. Min Act: -0.1700

Data Index: 8690731 (Open Web Text)

Max Activating Token Index: 774

Text #10

Max Range: 1.9207. Min Range: -1.9207

Max Act: 1.7670. Min Act: -0.1700

Data Index: 8695557 (Open Web Text)

Max Activating Token Index: 668

Text #11

Max Range: 1.9207. Min Range: -1.9207

Max Act: 1.7740. Min Act: -0.1678

Data Index: 8288014 (Open Web Text)

Max Activating Token Index: 220

Text #12

Max Range: 1.9207. Min Range: -1.9207

Max Act: 1.7218. Min Act: -0.1700

Data Index: 6952172 (Open Web Text)

Max Activating Token Index: 347

Text #13

Max Range: 1.9207. Min Range: -1.9207

Max Act: 1.7446. Min Act: -0.1700

Data Index: 5781584 (Open Web Text)

Max Activating Token Index: 449

Text #14

Max Range: 1.9207. Min Range: -1.9207

Max Act: 1.7252. Min Act: -0.1614

Data Index: 5931854 (Open Web Text)

Max Activating Token Index: 337

Text #15

Max Range: 1.9207. Min Range: -1.9207

Max Act: 1.7193. Min Act: -0.1700

Data Index: 6952173 (Open Web Text)

Max Activating Token Index: 548

Text #16

Max Range: 1.9207. Min Range: -1.9207

Max Act: 1.7264. Min Act: -0.1700

Data Index: 8288010 (Open Web Text)

Max Activating Token Index: 228

Text #17

Max Range: 1.9207. Min Range: -1.9207

Max Act: 1.7324. Min Act: -0.1700

Data Index: 2738607 (Open Web Text)

Max Activating Token Index: 415

Text #18

Max Range: 1.9207. Min Range: -1.9207

Max Act: 1.7124. Min Act: -0.1700

Data Index: 5077213 (Open Web Text)

Max Activating Token Index: 477

Text #19

Max Range: 1.9207. Min Range: -1.9207

Max Act: 1.7152. Min Act: -0.1700

Data Index: 7649850 (Open Web Text)

Max Activating Token Index: 200