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

Dataset: Open Web Text

Neuron 1048 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: 3.4786. Min Range: -3.4786

Max Act: 3.4786. Min Act: -0.1700

Data Index: 6527427 (Open Web Text)

Max Activating Token Index: 536

Text #1

Max Range: 3.4786. Min Range: -3.4786

Max Act: 3.4711. Min Act: -0.1700

Data Index: 2902396 (Open Web Text)

Max Activating Token Index: 349

Text #2

Max Range: 3.4786. Min Range: -3.4786

Max Act: 3.4596. Min Act: -0.1700

Data Index: 4266501 (Open Web Text)

Max Activating Token Index: 224

Text #3

Max Range: 3.4786. Min Range: -3.4786

Max Act: 3.4458. Min Act: -0.1700

Data Index: 6493605 (Open Web Text)

Max Activating Token Index: 454

Text #4

Max Range: 3.4786. Min Range: -3.4786

Max Act: 3.4574. Min Act: -0.1700

Data Index: 7514042 (Open Web Text)

Max Activating Token Index: 184

Text #5

Max Range: 3.4786. Min Range: -3.4786

Max Act: 3.4333. Min Act: -0.1700

Data Index: 7050865 (Open Web Text)

Max Activating Token Index: 888

Text #6

Max Range: 3.4786. Min Range: -3.4786

Max Act: 3.4099. Min Act: -0.1700

Data Index: 8095246 (Open Web Text)

Max Activating Token Index: 904

Text #7

Max Range: 3.4786. Min Range: -3.4786

Max Act: 3.4204. Min Act: -0.1700

Data Index: 6014359 (Open Web Text)

Max Activating Token Index: 550

Text #8

Max Range: 3.4786. Min Range: -3.4786

Max Act: 3.4297. Min Act: -0.1700

Data Index: 879912 (Open Web Text)

Max Activating Token Index: 648

Text #9

Max Range: 3.4786. Min Range: -3.4786

Max Act: 3.4075. Min Act: -0.1700

Data Index: 2676878 (Open Web Text)

Max Activating Token Index: 826

Text #10

Max Range: 3.4786. Min Range: -3.4786

Max Act: 3.3933. Min Act: -0.1700

Data Index: 2357080 (Open Web Text)

Max Activating Token Index: 538

Text #11

Max Range: 3.4786. Min Range: -3.4786

Max Act: 3.3932. Min Act: -0.1700

Data Index: 1942520 (Open Web Text)

Max Activating Token Index: 487

Text #12

Max Range: 3.4786. Min Range: -3.4786

Max Act: 3.3945. Min Act: -0.1700

Data Index: 696042 (Open Web Text)

Max Activating Token Index: 529

Text #13

Max Range: 3.4786. Min Range: -3.4786

Max Act: 3.3879. Min Act: -0.1700

Data Index: 2415120 (Open Web Text)

Max Activating Token Index: 758

Text #14

Max Range: 3.4786. Min Range: -3.4786

Max Act: 3.3978. Min Act: -0.1700

Data Index: 4163094 (Open Web Text)

Max Activating Token Index: 359

Text #15

Max Range: 3.4786. Min Range: -3.4786

Max Act: 3.3951. Min Act: -0.1700

Data Index: 7002114 (Open Web Text)

Max Activating Token Index: 639

Text #16

Max Range: 3.4786. Min Range: -3.4786

Max Act: 3.4079. Min Act: -0.1700

Data Index: 6126311 (Open Web Text)

Max Activating Token Index: 402

Text #17

Max Range: 3.4786. Min Range: -3.4786

Max Act: 3.3936. Min Act: -0.1700

Data Index: 1419342 (Open Web Text)

Max Activating Token Index: 430

Text #18

Max Range: 3.4786. Min Range: -3.4786

Max Act: 3.3873. Min Act: -0.1700

Data Index: 7161140 (Open Web Text)

Max Activating Token Index: 886

Text #19

Max Range: 3.4786. Min Range: -3.4786

Max Act: 3.3795. Min Act: -0.1700

Data Index: 2786826 (Open Web Text)

Max Activating Token Index: 152