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

Dataset: Open Web Text

Neuron 2658 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: 3.5641. Min Range: -3.5641

Max Act: 3.5641. Min Act: -0.1700

Data Index: 2480906 (Open Web Text)

Max Activating Token Index: 784

Text #1

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.5205. Min Act: -0.1700

Data Index: 8466400 (Open Web Text)

Max Activating Token Index: 487

Text #2

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.4987. Min Act: -0.1700

Data Index: 2681756 (Open Web Text)

Max Activating Token Index: 876

Text #3

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.4716. Min Act: -0.1700

Data Index: 2902138 (Open Web Text)

Max Activating Token Index: 608

Text #4

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.4982. Min Act: -0.1700

Data Index: 939899 (Open Web Text)

Max Activating Token Index: 721

Text #5

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.4819. Min Act: -0.1700

Data Index: 8166831 (Open Web Text)

Max Activating Token Index: 379

Text #6

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.4620. Min Act: -0.1700

Data Index: 3403156 (Open Web Text)

Max Activating Token Index: 418

Text #7

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.4991. Min Act: -0.1700

Data Index: 2281041 (Open Web Text)

Max Activating Token Index: 402

Text #8

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.4572. Min Act: -0.1700

Data Index: 8148832 (Open Web Text)

Max Activating Token Index: 782

Text #9

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.4910. Min Act: -0.1700

Data Index: 1772318 (Open Web Text)

Max Activating Token Index: 640

Text #10

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.4646. Min Act: -0.1700

Data Index: 7181511 (Open Web Text)

Max Activating Token Index: 794

Text #11

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.4528. Min Act: -0.1700

Data Index: 4777051 (Open Web Text)

Max Activating Token Index: 434

Text #12

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.4741. Min Act: -0.1700

Data Index: 4028429 (Open Web Text)

Max Activating Token Index: 874

Text #13

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.4635. Min Act: -0.1700

Data Index: 6961408 (Open Web Text)

Max Activating Token Index: 264

Text #14

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.4550. Min Act: -0.1700

Data Index: 4279363 (Open Web Text)

Max Activating Token Index: 829

Text #15

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.4658. Min Act: -0.1700

Data Index: 7664895 (Open Web Text)

Max Activating Token Index: 269

Text #16

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.4586. Min Act: -0.1700

Data Index: 3641782 (Open Web Text)

Max Activating Token Index: 635

Text #17

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.4548. Min Act: -0.1700

Data Index: 5789577 (Open Web Text)

Max Activating Token Index: 457

Text #18

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.4387. Min Act: -0.1700

Data Index: 1408165 (Open Web Text)

Max Activating Token Index: 527

Text #19

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.4490. Min Act: -0.1700

Data Index: 8039275 (Open Web Text)

Max Activating Token Index: 769