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

Dataset: Open Web Text

Neuron 597 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: 3.6278. Min Range: -3.6278

Max Act: 3.6278. Min Act: -0.1700

Data Index: 5458732 (Open Web Text)

Max Activating Token Index: 610

Text #1

Max Range: 3.6278. Min Range: -3.6278

Max Act: 3.5810. Min Act: -0.1700

Data Index: 6258221 (Open Web Text)

Max Activating Token Index: 525

Text #2

Max Range: 3.6278. Min Range: -3.6278

Max Act: 3.6042. Min Act: -0.1700

Data Index: 5754663 (Open Web Text)

Max Activating Token Index: 309

Text #3

Max Range: 3.6278. Min Range: -3.6278

Max Act: 3.5598. Min Act: -0.1700

Data Index: 933649 (Open Web Text)

Max Activating Token Index: 819

Text #4

Max Range: 3.6278. Min Range: -3.6278

Max Act: 3.5366. Min Act: -0.1700

Data Index: 3011750 (Open Web Text)

Max Activating Token Index: 417

Text #5

Max Range: 3.6278. Min Range: -3.6278

Max Act: 3.5330. Min Act: -0.1700

Data Index: 2789505 (Open Web Text)

Max Activating Token Index: 761

Text #6

Max Range: 3.6278. Min Range: -3.6278

Max Act: 3.5344. Min Act: -0.1700

Data Index: 5613491 (Open Web Text)

Max Activating Token Index: 35

Text #7

Max Range: 3.6278. Min Range: -3.6278

Max Act: 3.5602. Min Act: -0.1700

Data Index: 5351927 (Open Web Text)

Max Activating Token Index: 357

Text #8

Max Range: 3.6278. Min Range: -3.6278

Max Act: 3.5414. Min Act: -0.1700

Data Index: 1956145 (Open Web Text)

Max Activating Token Index: 430

Text #9

Max Range: 3.6278. Min Range: -3.6278

Max Act: 3.5320. Min Act: -0.1700

Data Index: 3469246 (Open Web Text)

Max Activating Token Index: 51

Text #10

Max Range: 3.6278. Min Range: -3.6278

Max Act: 3.5293. Min Act: -0.1700

Data Index: 3121800 (Open Web Text)

Max Activating Token Index: 512

Text #11

Max Range: 3.6278. Min Range: -3.6278

Max Act: 3.5360. Min Act: -0.1700

Data Index: 2415359 (Open Web Text)

Max Activating Token Index: 114

Text #12

Max Range: 3.6278. Min Range: -3.6278

Max Act: 3.5052. Min Act: -0.1700

Data Index: 1375665 (Open Web Text)

Max Activating Token Index: 380

Text #13

Max Range: 3.6278. Min Range: -3.6278

Max Act: 3.5202. Min Act: -0.1700

Data Index: 7833076 (Open Web Text)

Max Activating Token Index: 676

Text #14

Max Range: 3.6278. Min Range: -3.6278

Max Act: 3.5649. Min Act: -0.1700

Data Index: 1853091 (Open Web Text)

Max Activating Token Index: 630

Text #15

Max Range: 3.6278. Min Range: -3.6278

Max Act: 3.5331. Min Act: -0.1700

Data Index: 2505025 (Open Web Text)

Max Activating Token Index: 368

Text #16

Max Range: 3.6278. Min Range: -3.6278

Max Act: 3.5168. Min Act: -0.1700

Data Index: 8021040 (Open Web Text)

Max Activating Token Index: 528

Text #17

Max Range: 3.6278. Min Range: -3.6278

Max Act: 3.5035. Min Act: -0.1700

Data Index: 8242225 (Open Web Text)

Max Activating Token Index: 385

Text #18

Max Range: 3.6278. Min Range: -3.6278

Max Act: 3.5063. Min Act: -0.1700

Data Index: 4518790 (Open Web Text)

Max Activating Token Index: 59

Text #19

Max Range: 3.6278. Min Range: -3.6278

Max Act: 3.5115. Min Act: -0.1700

Data Index: 3853975 (Open Web Text)

Max Activating Token Index: 679