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

Dataset: Open Web Text

Neuron 2054 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: 3.9249. Min Range: -3.9249

Max Act: 3.9249. Min Act: -0.1700

Data Index: 1308195 (Open Web Text)

Max Activating Token Index: 185

Text #1

Max Range: 3.9249. Min Range: -3.9249

Max Act: 3.8425. Min Act: -0.1700

Data Index: 7971933 (Open Web Text)

Max Activating Token Index: 128

Text #2

Max Range: 3.9249. Min Range: -3.9249

Max Act: 3.8295. Min Act: -0.1700

Data Index: 7992805 (Open Web Text)

Max Activating Token Index: 351

Text #3

Max Range: 3.9249. Min Range: -3.9249

Max Act: 3.7623. Min Act: -0.1700

Data Index: 4356138 (Open Web Text)

Max Activating Token Index: 473

Text #4

Max Range: 3.9249. Min Range: -3.9249

Max Act: 3.7240. Min Act: -0.1700

Data Index: 4562995 (Open Web Text)

Max Activating Token Index: 263

Text #5

Max Range: 3.9249. Min Range: -3.9249

Max Act: 3.7282. Min Act: -0.1700

Data Index: 1115323 (Open Web Text)

Max Activating Token Index: 296

Text #6

Max Range: 3.9249. Min Range: -3.9249

Max Act: 3.6762. Min Act: -0.1700

Data Index: 6772589 (Open Web Text)

Max Activating Token Index: 853

Text #7

Max Range: 3.9249. Min Range: -3.9249

Max Act: 3.6596. Min Act: -0.1700

Data Index: 430825 (Open Web Text)

Max Activating Token Index: 276

Text #8

Max Range: 3.9249. Min Range: -3.9249

Max Act: 3.6588. Min Act: -0.1700

Data Index: 1306583 (Open Web Text)

Max Activating Token Index: 232

Text #9

Max Range: 3.9249. Min Range: -3.9249

Max Act: 3.6751. Min Act: -0.1700

Data Index: 2046751 (Open Web Text)

Max Activating Token Index: 675

Text #10

Max Range: 3.9249. Min Range: -3.9249

Max Act: 3.6745. Min Act: -0.1700

Data Index: 4826237 (Open Web Text)

Max Activating Token Index: 264

Text #11

Max Range: 3.9249. Min Range: -3.9249

Max Act: 3.6283. Min Act: -0.1700

Data Index: 2441721 (Open Web Text)

Max Activating Token Index: 256

Text #12

Max Range: 3.9249. Min Range: -3.9249

Max Act: 3.6815. Min Act: -0.1700

Data Index: 6211462 (Open Web Text)

Max Activating Token Index: 429

Text #13

Max Range: 3.9249. Min Range: -3.9249

Max Act: 3.6451. Min Act: -0.1700

Data Index: 1726343 (Open Web Text)

Max Activating Token Index: 211

Text #14

Max Range: 3.9249. Min Range: -3.9249

Max Act: 3.6275. Min Act: -0.1700

Data Index: 4768607 (Open Web Text)

Max Activating Token Index: 333

Text #15

Max Range: 3.9249. Min Range: -3.9249

Max Act: 3.6520. Min Act: -0.1700

Data Index: 5731240 (Open Web Text)

Max Activating Token Index: 482

Text #16

Max Range: 3.9249. Min Range: -3.9249

Max Act: 3.6251. Min Act: -0.1700

Data Index: 676685 (Open Web Text)

Max Activating Token Index: 319

Text #17

Max Range: 3.9249. Min Range: -3.9249

Max Act: 3.6452. Min Act: -0.1700

Data Index: 5619868 (Open Web Text)

Max Activating Token Index: 277

Text #18

Max Range: 3.9249. Min Range: -3.9249

Max Act: 3.6223. Min Act: -0.1700

Data Index: 7276303 (Open Web Text)

Max Activating Token Index: 334

Text #19

Max Range: 3.9249. Min Range: -3.9249

Max Act: 3.6101. Min Act: -0.1700

Data Index: 6492367 (Open Web Text)

Max Activating Token Index: 316