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

Dataset: Open Web Text

Neuron 1028 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: 4.8622. Min Range: -4.8622

Max Act: 4.8413. Min Act: -0.1700

Data Index: 6498122 (Open Web Text)

Max Activating Token Index: 661

Text #1

Max Range: 4.8622. Min Range: -4.8622

Max Act: 4.8622. Min Act: -0.1700

Data Index: 1397760 (Open Web Text)

Max Activating Token Index: 476

Text #2

Max Range: 4.8622. Min Range: -4.8622

Max Act: 4.8480. Min Act: -0.1700

Data Index: 4435175 (Open Web Text)

Max Activating Token Index: 159

Text #3

Max Range: 4.8622. Min Range: -4.8622

Max Act: 4.7978. Min Act: -0.1700

Data Index: 6928992 (Open Web Text)

Max Activating Token Index: 415

Text #4

Max Range: 4.8622. Min Range: -4.8622

Max Act: 4.8385. Min Act: -0.1700

Data Index: 3801167 (Open Web Text)

Max Activating Token Index: 675

Text #5

Max Range: 4.8622. Min Range: -4.8622

Max Act: 4.8212. Min Act: -0.1700

Data Index: 3695847 (Open Web Text)

Max Activating Token Index: 931

Text #6

Max Range: 4.8622. Min Range: -4.8622

Max Act: 4.7993. Min Act: -0.1700

Data Index: 7807407 (Open Web Text)

Max Activating Token Index: 366

Text #7

Max Range: 4.8622. Min Range: -4.8622

Max Act: 4.8164. Min Act: -0.1700

Data Index: 5883263 (Open Web Text)

Max Activating Token Index: 253

Text #8

Max Range: 4.8622. Min Range: -4.8622

Max Act: 4.7844. Min Act: -0.1700

Data Index: 3468034 (Open Web Text)

Max Activating Token Index: 505

Text #9

Max Range: 4.8622. Min Range: -4.8622

Max Act: 4.7862. Min Act: -0.1700

Data Index: 3759330 (Open Web Text)

Max Activating Token Index: 152

Text #10

Max Range: 4.8622. Min Range: -4.8622

Max Act: 4.7902. Min Act: -0.1700

Data Index: 4790310 (Open Web Text)

Max Activating Token Index: 466

Text #11

Max Range: 4.8622. Min Range: -4.8622

Max Act: 4.7665. Min Act: -0.1700

Data Index: 4435174 (Open Web Text)

Max Activating Token Index: 855

Text #12

Max Range: 4.8622. Min Range: -4.8622

Max Act: 4.7795. Min Act: -0.1700

Data Index: 7161436 (Open Web Text)

Max Activating Token Index: 461

Text #13

Max Range: 4.8622. Min Range: -4.8622

Max Act: 4.7802. Min Act: -0.1700

Data Index: 7075321 (Open Web Text)

Max Activating Token Index: 376

Text #14

Max Range: 4.8622. Min Range: -4.8622

Max Act: 4.7608. Min Act: -0.1700

Data Index: 3491683 (Open Web Text)

Max Activating Token Index: 486

Text #15

Max Range: 4.8622. Min Range: -4.8622

Max Act: 4.7554. Min Act: -0.1700

Data Index: 1048662 (Open Web Text)

Max Activating Token Index: 605

Text #16

Max Range: 4.8622. Min Range: -4.8622

Max Act: 4.7427. Min Act: -0.1700

Data Index: 506633 (Open Web Text)

Max Activating Token Index: 592

Text #17

Max Range: 4.8622. Min Range: -4.8622

Max Act: 4.7405. Min Act: -0.1700

Data Index: 6191153 (Open Web Text)

Max Activating Token Index: 568

Text #18

Max Range: 4.8622. Min Range: -4.8622

Max Act: 4.7685. Min Act: -0.1700

Data Index: 6379413 (Open Web Text)

Max Activating Token Index: 402

Text #19

Max Range: 4.8622. Min Range: -4.8622

Max Act: 4.7375. Min Act: -0.1700

Data Index: 4040506 (Open Web Text)

Max Activating Token Index: 334