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

Dataset: Open Web Text

Neuron 134 in Layer 6

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: 3.6374. Min Range: -3.6374

Max Act: 3.6374. Min Act: -0.1700

Data Index: 7191151 (Open Web Text)

Max Activating Token Index: 77

Text #1

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.6235. Min Act: -0.1700

Data Index: 2054587 (Open Web Text)

Max Activating Token Index: 399

Text #2

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.5927. Min Act: -0.1700

Data Index: 6055885 (Open Web Text)

Max Activating Token Index: 368

Text #3

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.5802. Min Act: -0.1700

Data Index: 3801039 (Open Web Text)

Max Activating Token Index: 495

Text #4

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.5561. Min Act: -0.1700

Data Index: 8171777 (Open Web Text)

Max Activating Token Index: 192

Text #5

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.5519. Min Act: -0.1700

Data Index: 6408072 (Open Web Text)

Max Activating Token Index: 581

Text #6

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.5505. Min Act: -0.1700

Data Index: 1401695 (Open Web Text)

Max Activating Token Index: 233

Text #7

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.5378. Min Act: -0.1700

Data Index: 6952225 (Open Web Text)

Max Activating Token Index: 268

Text #8

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.5024. Min Act: -0.1700

Data Index: 5323509 (Open Web Text)

Max Activating Token Index: 735

Text #9

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.5122. Min Act: -0.1700

Data Index: 2332985 (Open Web Text)

Max Activating Token Index: 520

Text #10

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.4997. Min Act: -0.1700

Data Index: 1070352 (Open Web Text)

Max Activating Token Index: 547

Text #11

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.4929. Min Act: -0.1700

Data Index: 7186253 (Open Web Text)

Max Activating Token Index: 282

Text #12

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.4837. Min Act: -0.1700

Data Index: 2071914 (Open Web Text)

Max Activating Token Index: 370

Text #13

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.4709. Min Act: -0.1700

Data Index: 3395723 (Open Web Text)

Max Activating Token Index: 803

Text #14

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.4634. Min Act: -0.1700

Data Index: 7599407 (Open Web Text)

Max Activating Token Index: 150

Text #15

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.4567. Min Act: -0.1700

Data Index: 7057540 (Open Web Text)

Max Activating Token Index: 583

Text #16

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.4444. Min Act: -0.1700

Data Index: 8065071 (Open Web Text)

Max Activating Token Index: 410

Text #17

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.4332. Min Act: -0.1700

Data Index: 1574479 (Open Web Text)

Max Activating Token Index: 321

Text #18

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.4291. Min Act: -0.1700

Data Index: 7087031 (Open Web Text)

Max Activating Token Index: 78

Text #19

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.4411. Min Act: -0.1700

Data Index: 4750296 (Open Web Text)

Max Activating Token Index: 555