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

Dataset: Open Web Text

Neuron 1900 in Layer 3

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: 4.5782. Min Range: -4.5782

Max Act: 4.5782. Min Act: -0.1700

Data Index: 5256766 (Open Web Text)

Max Activating Token Index: 241

Text #1

Max Range: 4.5782. Min Range: -4.5782

Max Act: 4.5527. Min Act: -0.1700

Data Index: 5991338 (Open Web Text)

Max Activating Token Index: 476

Text #2

Max Range: 4.5782. Min Range: -4.5782

Max Act: 4.5418. Min Act: -0.1700

Data Index: 6233227 (Open Web Text)

Max Activating Token Index: 793

Text #3

Max Range: 4.5782. Min Range: -4.5782

Max Act: 4.5027. Min Act: -0.1700

Data Index: 3177614 (Open Web Text)

Max Activating Token Index: 474

Text #4

Max Range: 4.5782. Min Range: -4.5782

Max Act: 4.4478. Min Act: -0.1700

Data Index: 7832980 (Open Web Text)

Max Activating Token Index: 535

Text #5

Max Range: 4.5782. Min Range: -4.5782

Max Act: 4.4100. Min Act: -0.1700

Data Index: 5499562 (Open Web Text)

Max Activating Token Index: 668

Text #6

Max Range: 4.5782. Min Range: -4.5782

Max Act: 4.4575. Min Act: -0.1700

Data Index: 5048147 (Open Web Text)

Max Activating Token Index: 688

Text #7

Max Range: 4.5782. Min Range: -4.5782

Max Act: 4.4301. Min Act: -0.1700

Data Index: 3234591 (Open Web Text)

Max Activating Token Index: 787

Text #8

Max Range: 4.5782. Min Range: -4.5782

Max Act: 4.4393. Min Act: -0.1700

Data Index: 853486 (Open Web Text)

Max Activating Token Index: 1013

Text #9

Max Range: 4.5782. Min Range: -4.5782

Max Act: 4.4304. Min Act: -0.1700

Data Index: 3868478 (Open Web Text)

Max Activating Token Index: 329

Text #10

Max Range: 4.5782. Min Range: -4.5782

Max Act: 4.4134. Min Act: -0.1700

Data Index: 1518534 (Open Web Text)

Max Activating Token Index: 836

Text #11

Max Range: 4.5782. Min Range: -4.5782

Max Act: 4.4370. Min Act: -0.1700

Data Index: 3329524 (Open Web Text)

Max Activating Token Index: 1005

Text #12

Max Range: 4.5782. Min Range: -4.5782

Max Act: 4.3934. Min Act: -0.1700

Data Index: 6921042 (Open Web Text)

Max Activating Token Index: 497

Text #13

Max Range: 4.5782. Min Range: -4.5782

Max Act: 4.3810. Min Act: -0.1700

Data Index: 7012535 (Open Web Text)

Max Activating Token Index: 368

Text #14

Max Range: 4.5782. Min Range: -4.5782

Max Act: 4.3842. Min Act: -0.1700

Data Index: 7647547 (Open Web Text)

Max Activating Token Index: 370

Text #15

Max Range: 4.5782. Min Range: -4.5782

Max Act: 4.3620. Min Act: -0.1700

Data Index: 857086 (Open Web Text)

Max Activating Token Index: 327

Text #16

Max Range: 4.5782. Min Range: -4.5782

Max Act: 4.3701. Min Act: -0.1700

Data Index: 6627935 (Open Web Text)

Max Activating Token Index: 441

Text #17

Max Range: 4.5782. Min Range: -4.5782

Max Act: 4.3890. Min Act: -0.1700

Data Index: 1195032 (Open Web Text)

Max Activating Token Index: 482

Text #18

Max Range: 4.5782. Min Range: -4.5782

Max Act: 4.3835. Min Act: -0.1700

Data Index: 3705519 (Open Web Text)

Max Activating Token Index: 457

Text #19

Max Range: 4.5782. Min Range: -4.5782

Max Act: 4.3986. Min Act: -0.1700

Data Index: 869528 (Open Web Text)

Max Activating Token Index: 304