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

Dataset: Open Web Text

Neuron 101 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: 0.9967. Min Range: -0.9967

Max Act: 0.9967. Min Act: -0.1616

Data Index: 8021073 (Open Web Text)

Max Activating Token Index: 525

Text #1

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9798. Min Act: -0.1462

Data Index: 4137266 (Open Web Text)

Max Activating Token Index: 1014

Text #2

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9785. Min Act: -0.1635

Data Index: 7933539 (Open Web Text)

Max Activating Token Index: 527

Text #3

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9690. Min Act: -0.1448

Data Index: 1642930 (Open Web Text)

Max Activating Token Index: 331

Text #4

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9546. Min Act: -0.1668

Data Index: 4603390 (Open Web Text)

Max Activating Token Index: 723

Text #5

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9529. Min Act: -0.1637

Data Index: 4576046 (Open Web Text)

Max Activating Token Index: 333

Text #6

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9440. Min Act: -0.1387

Data Index: 7393978 (Open Web Text)

Max Activating Token Index: 258

Text #7

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9468. Min Act: -0.1367

Data Index: 2117765 (Open Web Text)

Max Activating Token Index: 977

Text #8

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9419. Min Act: -0.1444

Data Index: 203941 (Open Web Text)

Max Activating Token Index: 254

Text #9

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9403. Min Act: -0.1404

Data Index: 1262934 (Open Web Text)

Max Activating Token Index: 413

Text #10

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9447. Min Act: -0.1240

Data Index: 5610055 (Open Web Text)

Max Activating Token Index: 949

Text #11

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9374. Min Act: -0.1678

Data Index: 5519940 (Open Web Text)

Max Activating Token Index: 148

Text #12

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9323. Min Act: -0.1438

Data Index: 4064196 (Open Web Text)

Max Activating Token Index: 711

Text #13

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9318. Min Act: -0.1558

Data Index: 4296292 (Open Web Text)

Max Activating Token Index: 336

Text #14

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9281. Min Act: -0.1601

Data Index: 1823352 (Open Web Text)

Max Activating Token Index: 865

Text #15

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9283. Min Act: -0.1313

Data Index: 4218636 (Open Web Text)

Max Activating Token Index: 1008

Text #16

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9208. Min Act: -0.1602

Data Index: 2286359 (Open Web Text)

Max Activating Token Index: 1006

Text #17

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9220. Min Act: -0.1299

Data Index: 747991 (Open Web Text)

Max Activating Token Index: 396

Text #18

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9240. Min Act: -0.1581

Data Index: 99054 (Open Web Text)

Max Activating Token Index: 639

Text #19

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9125. Min Act: -0.1184

Data Index: 177741 (Open Web Text)

Max Activating Token Index: 898