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

Dataset: Open Web Text

Neuron 863 in Layer 1

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: 4.7163. Min Range: -4.7163

Max Act: 4.7144. Min Act: -0.1700

Data Index: 4585051 (Open Web Text)

Max Activating Token Index: 175

Text #1

Max Range: 4.7163. Min Range: -4.7163

Max Act: 4.7082. Min Act: -0.1700

Data Index: 4724222 (Open Web Text)

Max Activating Token Index: 47

Text #2

Max Range: 4.7163. Min Range: -4.7163

Max Act: 4.7163. Min Act: -0.1700

Data Index: 5382749 (Open Web Text)

Max Activating Token Index: 195

Text #3

Max Range: 4.7163. Min Range: -4.7163

Max Act: 4.6807. Min Act: -0.1700

Data Index: 4167201 (Open Web Text)

Max Activating Token Index: 327

Text #4

Max Range: 4.7163. Min Range: -4.7163

Max Act: 4.6618. Min Act: -0.1700

Data Index: 8597364 (Open Web Text)

Max Activating Token Index: 452

Text #5

Max Range: 4.7163. Min Range: -4.7163

Max Act: 4.6864. Min Act: -0.1700

Data Index: 3001807 (Open Web Text)

Max Activating Token Index: 596

Text #6

Max Range: 4.7163. Min Range: -4.7163

Max Act: 4.6581. Min Act: -0.1700

Data Index: 6791144 (Open Web Text)

Max Activating Token Index: 220

Text #7

Max Range: 4.7163. Min Range: -4.7163

Max Act: 4.6211. Min Act: -0.1700

Data Index: 6917503 (Open Web Text)

Max Activating Token Index: 593

Text #8

Max Range: 4.7163. Min Range: -4.7163

Max Act: 4.6464. Min Act: -0.1700

Data Index: 3143770 (Open Web Text)

Max Activating Token Index: 465

Text #9

Max Range: 4.7163. Min Range: -4.7163

Max Act: 4.6316. Min Act: -0.1700

Data Index: 7460830 (Open Web Text)

Max Activating Token Index: 258

Text #10

Max Range: 4.7163. Min Range: -4.7163

Max Act: 4.6537. Min Act: -0.1700

Data Index: 964198 (Open Web Text)

Max Activating Token Index: 308

Text #11

Max Range: 4.7163. Min Range: -4.7163

Max Act: 4.6416. Min Act: -0.1700

Data Index: 269400 (Open Web Text)

Max Activating Token Index: 598

Text #12

Max Range: 4.7163. Min Range: -4.7163

Max Act: 4.6421. Min Act: -0.1700

Data Index: 7627185 (Open Web Text)

Max Activating Token Index: 605

Text #13

Max Range: 4.7163. Min Range: -4.7163

Max Act: 4.6495. Min Act: -0.1699

Data Index: 3803103 (Open Web Text)

Max Activating Token Index: 425

Text #14

Max Range: 4.7163. Min Range: -4.7163

Max Act: 4.6192. Min Act: -0.1700

Data Index: 8227724 (Open Web Text)

Max Activating Token Index: 219

Text #15

Max Range: 4.7163. Min Range: -4.7163

Max Act: 4.6517. Min Act: -0.1700

Data Index: 8386192 (Open Web Text)

Max Activating Token Index: 163

Text #16

Max Range: 4.7163. Min Range: -4.7163

Max Act: 4.6393. Min Act: -0.1700

Data Index: 5307149 (Open Web Text)

Max Activating Token Index: 554

Text #17

Max Range: 4.7163. Min Range: -4.7163

Max Act: 4.6562. Min Act: -0.1700

Data Index: 1328785 (Open Web Text)

Max Activating Token Index: 605

Text #18

Max Range: 4.7163. Min Range: -4.7163

Max Act: 4.6319. Min Act: -0.1700

Data Index: 1924807 (Open Web Text)

Max Activating Token Index: 421

Text #19

Max Range: 4.7163. Min Range: -4.7163

Max Act: 4.5984. Min Act: -0.1700

Data Index: 1417056 (Open Web Text)

Max Activating Token Index: 339