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

Dataset: Open Web Text

Neuron 1696 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: 3.6375. Min Range: -3.6375

Max Act: 3.6375. Min Act: -0.1700

Data Index: 6881429 (Open Web Text)

Max Activating Token Index: 534

Text #1

Max Range: 3.6375. Min Range: -3.6375

Max Act: 3.6258. Min Act: -0.1700

Data Index: 4965391 (Open Web Text)

Max Activating Token Index: 487

Text #2

Max Range: 3.6375. Min Range: -3.6375

Max Act: 3.5877. Min Act: -0.1700

Data Index: 4006042 (Open Web Text)

Max Activating Token Index: 813

Text #3

Max Range: 3.6375. Min Range: -3.6375

Max Act: 3.5687. Min Act: -0.1700

Data Index: 2703817 (Open Web Text)

Max Activating Token Index: 547

Text #4

Max Range: 3.6375. Min Range: -3.6375

Max Act: 3.5079. Min Act: -0.1700

Data Index: 3920776 (Open Web Text)

Max Activating Token Index: 829

Text #5

Max Range: 3.6375. Min Range: -3.6375

Max Act: 3.5589. Min Act: -0.1700

Data Index: 6182885 (Open Web Text)

Max Activating Token Index: 216

Text #6

Max Range: 3.6375. Min Range: -3.6375

Max Act: 3.4976. Min Act: -0.1700

Data Index: 2141177 (Open Web Text)

Max Activating Token Index: 771

Text #7

Max Range: 3.6375. Min Range: -3.6375

Max Act: 3.5108. Min Act: -0.1700

Data Index: 2122399 (Open Web Text)

Max Activating Token Index: 635

Text #8

Max Range: 3.6375. Min Range: -3.6375

Max Act: 3.4975. Min Act: -0.1700

Data Index: 7691363 (Open Web Text)

Max Activating Token Index: 350

Text #9

Max Range: 3.6375. Min Range: -3.6375

Max Act: 3.4818. Min Act: -0.1700

Data Index: 4837051 (Open Web Text)

Max Activating Token Index: 715

Text #10

Max Range: 3.6375. Min Range: -3.6375

Max Act: 3.4878. Min Act: -0.1700

Data Index: 3675988 (Open Web Text)

Max Activating Token Index: 581

Text #11

Max Range: 3.6375. Min Range: -3.6375

Max Act: 3.4765. Min Act: -0.1700

Data Index: 4976709 (Open Web Text)

Max Activating Token Index: 72

Text #12

Max Range: 3.6375. Min Range: -3.6375

Max Act: 3.4682. Min Act: -0.1700

Data Index: 8522419 (Open Web Text)

Max Activating Token Index: 375

Text #13

Max Range: 3.6375. Min Range: -3.6375

Max Act: 3.4668. Min Act: -0.1700

Data Index: 3560411 (Open Web Text)

Max Activating Token Index: 230

Text #14

Max Range: 3.6375. Min Range: -3.6375

Max Act: 3.4641. Min Act: -0.1700

Data Index: 219744 (Open Web Text)

Max Activating Token Index: 192

Text #15

Max Range: 3.6375. Min Range: -3.6375

Max Act: 3.4626. Min Act: -0.1700

Data Index: 2031518 (Open Web Text)

Max Activating Token Index: 74

Text #16

Max Range: 3.6375. Min Range: -3.6375

Max Act: 3.4459. Min Act: -0.1700

Data Index: 5782666 (Open Web Text)

Max Activating Token Index: 416

Text #17

Max Range: 3.6375. Min Range: -3.6375

Max Act: 3.4400. Min Act: -0.1700

Data Index: 795894 (Open Web Text)

Max Activating Token Index: 948

Text #18

Max Range: 3.6375. Min Range: -3.6375

Max Act: 3.4419. Min Act: -0.1700

Data Index: 4435744 (Open Web Text)

Max Activating Token Index: 996

Text #19

Max Range: 3.6375. Min Range: -3.6375

Max Act: 3.4432. Min Act: -0.1700

Data Index: 4416049 (Open Web Text)

Max Activating Token Index: 614