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

Dataset: Open Web Text

Neuron 820 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: 4.1488. Min Range: -4.1488

Max Act: 4.1361. Min Act: -0.1700

Data Index: 5892709 (Open Web Text)

Max Activating Token Index: 664

Text #1

Max Range: 4.1488. Min Range: -4.1488

Max Act: 4.1488. Min Act: -0.1700

Data Index: 6633573 (Open Web Text)

Max Activating Token Index: 901

Text #2

Max Range: 4.1488. Min Range: -4.1488

Max Act: 4.0541. Min Act: -0.1700

Data Index: 1292404 (Open Web Text)

Max Activating Token Index: 1020

Text #3

Max Range: 4.1488. Min Range: -4.1488

Max Act: 4.0921. Min Act: -0.1700

Data Index: 4402434 (Open Web Text)

Max Activating Token Index: 617

Text #4

Max Range: 4.1488. Min Range: -4.1488

Max Act: 4.0610. Min Act: -0.1700

Data Index: 4716401 (Open Web Text)

Max Activating Token Index: 871

Text #5

Max Range: 4.1488. Min Range: -4.1488

Max Act: 3.9934. Min Act: -0.1700

Data Index: 6649532 (Open Web Text)

Max Activating Token Index: 476

Text #6

Max Range: 4.1488. Min Range: -4.1488

Max Act: 4.0663. Min Act: -0.1700

Data Index: 7079525 (Open Web Text)

Max Activating Token Index: 392

Text #7

Max Range: 4.1488. Min Range: -4.1488

Max Act: 4.0147. Min Act: -0.1700

Data Index: 8711178 (Open Web Text)

Max Activating Token Index: 974

Text #8

Max Range: 4.1488. Min Range: -4.1488

Max Act: 3.9917. Min Act: -0.1700

Data Index: 97526 (Open Web Text)

Max Activating Token Index: 263

Text #9

Max Range: 4.1488. Min Range: -4.1488

Max Act: 3.9894. Min Act: -0.1700

Data Index: 26408 (Open Web Text)

Max Activating Token Index: 986

Text #10

Max Range: 4.1488. Min Range: -4.1488

Max Act: 3.9937. Min Act: -0.1700

Data Index: 8603879 (Open Web Text)

Max Activating Token Index: 900

Text #11

Max Range: 4.1488. Min Range: -4.1488

Max Act: 4.0384. Min Act: -0.1700

Data Index: 1762428 (Open Web Text)

Max Activating Token Index: 546

Text #12

Max Range: 4.1488. Min Range: -4.1488

Max Act: 3.9894. Min Act: -0.1700

Data Index: 3840178 (Open Web Text)

Max Activating Token Index: 494

Text #13

Max Range: 4.1488. Min Range: -4.1488

Max Act: 4.0162. Min Act: -0.1700

Data Index: 7907152 (Open Web Text)

Max Activating Token Index: 468

Text #14

Max Range: 4.1488. Min Range: -4.1488

Max Act: 4.0268. Min Act: -0.1700

Data Index: 3745737 (Open Web Text)

Max Activating Token Index: 776

Text #15

Max Range: 4.1488. Min Range: -4.1488

Max Act: 4.0407. Min Act: -0.1700

Data Index: 7709400 (Open Web Text)

Max Activating Token Index: 574

Text #16

Max Range: 4.1488. Min Range: -4.1488

Max Act: 3.9995. Min Act: -0.1700

Data Index: 1630540 (Open Web Text)

Max Activating Token Index: 649

Text #17

Max Range: 4.1488. Min Range: -4.1488

Max Act: 4.0371. Min Act: -0.1700

Data Index: 3355984 (Open Web Text)

Max Activating Token Index: 467

Text #18

Max Range: 4.1488. Min Range: -4.1488

Max Act: 4.0322. Min Act: -0.1700

Data Index: 5474590 (Open Web Text)

Max Activating Token Index: 953

Text #19

Max Range: 4.1488. Min Range: -4.1488

Max Act: 4.0364. Min Act: -0.1700

Data Index: 4489991 (Open Web Text)

Max Activating Token Index: 365