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

Dataset: Open Web Text

Neuron 405 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: 3.1344. Min Range: -3.1344

Max Act: 3.1344. Min Act: -0.1700

Data Index: 7591294 (Open Web Text)

Max Activating Token Index: 106

Text #1

Max Range: 3.1344. Min Range: -3.1344

Max Act: 3.1286. Min Act: -0.1700

Data Index: 49333 (Open Web Text)

Max Activating Token Index: 242

Text #2

Max Range: 3.1344. Min Range: -3.1344

Max Act: 3.0222. Min Act: -0.1700

Data Index: 3981108 (Open Web Text)

Max Activating Token Index: 581

Text #3

Max Range: 3.1344. Min Range: -3.1344

Max Act: 3.0253. Min Act: -0.1700

Data Index: 6808143 (Open Web Text)

Max Activating Token Index: 288

Text #4

Max Range: 3.1344. Min Range: -3.1344

Max Act: 2.9703. Min Act: -0.1700

Data Index: 6774325 (Open Web Text)

Max Activating Token Index: 235

Text #5

Max Range: 3.1344. Min Range: -3.1344

Max Act: 2.9157. Min Act: -0.1700

Data Index: 6829793 (Open Web Text)

Max Activating Token Index: 267

Text #6

Max Range: 3.1344. Min Range: -3.1344

Max Act: 2.8989. Min Act: -0.1700

Data Index: 1077268 (Open Web Text)

Max Activating Token Index: 826

Text #7

Max Range: 3.1344. Min Range: -3.1344

Max Act: 2.8706. Min Act: -0.1700

Data Index: 4361524 (Open Web Text)

Max Activating Token Index: 210

Text #8

Max Range: 3.1344. Min Range: -3.1344

Max Act: 2.8370. Min Act: -0.1700

Data Index: 8797120 (Open Web Text)

Max Activating Token Index: 233

Text #9

Max Range: 3.1344. Min Range: -3.1344

Max Act: 2.9177. Min Act: -0.1700

Data Index: 140001 (Open Web Text)

Max Activating Token Index: 282

Text #10

Max Range: 3.1344. Min Range: -3.1344

Max Act: 2.8657. Min Act: -0.1700

Data Index: 8706648 (Open Web Text)

Max Activating Token Index: 187

Text #11

Max Range: 3.1344. Min Range: -3.1344

Max Act: 2.9165. Min Act: -0.1700

Data Index: 2214951 (Open Web Text)

Max Activating Token Index: 23

Text #12

Max Range: 3.1344. Min Range: -3.1344

Max Act: 2.8659. Min Act: -0.1700

Data Index: 859564 (Open Web Text)

Max Activating Token Index: 480

Text #13

Max Range: 3.1344. Min Range: -3.1344

Max Act: 2.8073. Min Act: -0.1700

Data Index: 7358583 (Open Web Text)

Max Activating Token Index: 836

Text #14

Max Range: 3.1344. Min Range: -3.1344

Max Act: 2.9079. Min Act: -0.1700

Data Index: 6557400 (Open Web Text)

Max Activating Token Index: 346

Text #15

Max Range: 3.1344. Min Range: -3.1344

Max Act: 2.9258. Min Act: -0.1700

Data Index: 7606813 (Open Web Text)

Max Activating Token Index: 610

Text #16

Max Range: 3.1344. Min Range: -3.1344

Max Act: 2.8491. Min Act: -0.1700

Data Index: 7592571 (Open Web Text)

Max Activating Token Index: 569

Text #17

Max Range: 3.1344. Min Range: -3.1344

Max Act: 2.9098. Min Act: -0.1700

Data Index: 8208732 (Open Web Text)

Max Activating Token Index: 503

Text #18

Max Range: 3.1344. Min Range: -3.1344

Max Act: 2.8385. Min Act: -0.1700

Data Index: 5485143 (Open Web Text)

Max Activating Token Index: 300

Text #19

Max Range: 3.1344. Min Range: -3.1344

Max Act: 2.8806. Min Act: -0.1700

Data Index: 2751770 (Open Web Text)

Max Activating Token Index: 451