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

Dataset: Open Web Text

Neuron 676 in Layer 5

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: 3.5348. Min Range: -3.5348

Max Act: 3.5348. Min Act: -0.1700

Data Index: 2225230 (Open Web Text)

Max Activating Token Index: 600

Text #1

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.5132. Min Act: -0.1700

Data Index: 8449292 (Open Web Text)

Max Activating Token Index: 90

Text #2

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4680. Min Act: -0.1700

Data Index: 4142402 (Open Web Text)

Max Activating Token Index: 251

Text #3

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4314. Min Act: -0.1700

Data Index: 5868199 (Open Web Text)

Max Activating Token Index: 719

Text #4

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4294. Min Act: -0.1700

Data Index: 5975981 (Open Web Text)

Max Activating Token Index: 369

Text #5

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.3990. Min Act: -0.1700

Data Index: 4800637 (Open Web Text)

Max Activating Token Index: 706

Text #6

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4089. Min Act: -0.1700

Data Index: 6549986 (Open Web Text)

Max Activating Token Index: 403

Text #7

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.4041. Min Act: -0.1700

Data Index: 4536545 (Open Web Text)

Max Activating Token Index: 510

Text #8

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.3831. Min Act: -0.1700

Data Index: 3569594 (Open Web Text)

Max Activating Token Index: 437

Text #9

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.3144. Min Act: -0.1700

Data Index: 3429107 (Open Web Text)

Max Activating Token Index: 842

Text #10

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.3436. Min Act: -0.1700

Data Index: 8666826 (Open Web Text)

Max Activating Token Index: 424

Text #11

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.3213. Min Act: -0.1700

Data Index: 575963 (Open Web Text)

Max Activating Token Index: 372

Text #12

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.3508. Min Act: -0.1700

Data Index: 6860771 (Open Web Text)

Max Activating Token Index: 360

Text #13

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.3124. Min Act: -0.1700

Data Index: 6495071 (Open Web Text)

Max Activating Token Index: 330

Text #14

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.3244. Min Act: -0.1700

Data Index: 3360987 (Open Web Text)

Max Activating Token Index: 743

Text #15

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.3209. Min Act: -0.1700

Data Index: 2843042 (Open Web Text)

Max Activating Token Index: 693

Text #16

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.2880. Min Act: -0.1700

Data Index: 7004988 (Open Web Text)

Max Activating Token Index: 426

Text #17

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.2751. Min Act: -0.1700

Data Index: 4536548 (Open Web Text)

Max Activating Token Index: 174

Text #18

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.2830. Min Act: -0.1700

Data Index: 4781726 (Open Web Text)

Max Activating Token Index: 280

Text #19

Max Range: 3.5348. Min Range: -3.5348

Max Act: 3.2781. Min Act: -0.1700

Data Index: 618426 (Open Web Text)

Max Activating Token Index: 76