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

Dataset: Open Web Text

Neuron 602 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: 3.0379. Min Range: -3.0379

Max Act: 3.0250. Min Act: -0.1700

Data Index: 5811809 (Open Web Text)

Max Activating Token Index: 476

Text #1

Max Range: 3.0379. Min Range: -3.0379

Max Act: 3.0379. Min Act: -0.1700

Data Index: 8704583 (Open Web Text)

Max Activating Token Index: 581

Text #2

Max Range: 3.0379. Min Range: -3.0379

Max Act: 3.0276. Min Act: -0.1700

Data Index: 897054 (Open Web Text)

Max Activating Token Index: 423

Text #3

Max Range: 3.0379. Min Range: -3.0379

Max Act: 3.0361. Min Act: -0.1700

Data Index: 1270565 (Open Web Text)

Max Activating Token Index: 240

Text #4

Max Range: 3.0379. Min Range: -3.0379

Max Act: 2.9978. Min Act: -0.1700

Data Index: 5679624 (Open Web Text)

Max Activating Token Index: 520

Text #5

Max Range: 3.0379. Min Range: -3.0379

Max Act: 2.9936. Min Act: -0.1700

Data Index: 2219775 (Open Web Text)

Max Activating Token Index: 406

Text #6

Max Range: 3.0379. Min Range: -3.0379

Max Act: 2.9707. Min Act: -0.1700

Data Index: 6148585 (Open Web Text)

Max Activating Token Index: 859

Text #7

Max Range: 3.0379. Min Range: -3.0379

Max Act: 2.9498. Min Act: -0.1700

Data Index: 6177351 (Open Web Text)

Max Activating Token Index: 787

Text #8

Max Range: 3.0379. Min Range: -3.0379

Max Act: 2.9707. Min Act: -0.1700

Data Index: 960176 (Open Web Text)

Max Activating Token Index: 355

Text #9

Max Range: 3.0379. Min Range: -3.0379

Max Act: 2.9573. Min Act: -0.1700

Data Index: 4149284 (Open Web Text)

Max Activating Token Index: 703

Text #10

Max Range: 3.0379. Min Range: -3.0379

Max Act: 2.9276. Min Act: -0.1700

Data Index: 6104777 (Open Web Text)

Max Activating Token Index: 460

Text #11

Max Range: 3.0379. Min Range: -3.0379

Max Act: 2.9340. Min Act: -0.1700

Data Index: 6245743 (Open Web Text)

Max Activating Token Index: 715

Text #12

Max Range: 3.0379. Min Range: -3.0379

Max Act: 2.9076. Min Act: -0.1700

Data Index: 2755044 (Open Web Text)

Max Activating Token Index: 672

Text #13

Max Range: 3.0379. Min Range: -3.0379

Max Act: 2.9078. Min Act: -0.1700

Data Index: 4299681 (Open Web Text)

Max Activating Token Index: 489

Text #14

Max Range: 3.0379. Min Range: -3.0379

Max Act: 2.9252. Min Act: -0.1700

Data Index: 8132606 (Open Web Text)

Max Activating Token Index: 344

Text #15

Max Range: 3.0379. Min Range: -3.0379

Max Act: 2.9361. Min Act: -0.1700

Data Index: 447377 (Open Web Text)

Max Activating Token Index: 793

Text #16

Max Range: 3.0379. Min Range: -3.0379

Max Act: 2.8999. Min Act: -0.1700

Data Index: 4372687 (Open Web Text)

Max Activating Token Index: 99

Text #17

Max Range: 3.0379. Min Range: -3.0379

Max Act: 2.8829. Min Act: -0.1700

Data Index: 1865683 (Open Web Text)

Max Activating Token Index: 832

Text #18

Max Range: 3.0379. Min Range: -3.0379

Max Act: 2.9208. Min Act: -0.1700

Data Index: 90114 (Open Web Text)

Max Activating Token Index: 964

Text #19

Max Range: 3.0379. Min Range: -3.0379

Max Act: 2.8933. Min Act: -0.1700

Data Index: 7081309 (Open Web Text)

Max Activating Token Index: 521