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

Dataset: Open Web Text

Neuron 442 in Layer 6

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: 5.9993. Min Range: -5.9993

Max Act: 5.9993. Min Act: -0.1700

Data Index: 7058344 (Open Web Text)

Max Activating Token Index: 509

Text #1

Max Range: 5.9993. Min Range: -5.9993

Max Act: 5.9371. Min Act: -0.1700

Data Index: 4579684 (Open Web Text)

Max Activating Token Index: 673

Text #2

Max Range: 5.9993. Min Range: -5.9993

Max Act: 5.9647. Min Act: -0.1700

Data Index: 1069179 (Open Web Text)

Max Activating Token Index: 637

Text #3

Max Range: 5.9993. Min Range: -5.9993

Max Act: 5.9242. Min Act: -0.1700

Data Index: 32441 (Open Web Text)

Max Activating Token Index: 655

Text #4

Max Range: 5.9993. Min Range: -5.9993

Max Act: 5.9053. Min Act: -0.1700

Data Index: 3936274 (Open Web Text)

Max Activating Token Index: 463

Text #5

Max Range: 5.9993. Min Range: -5.9993

Max Act: 5.9029. Min Act: -0.1700

Data Index: 6825379 (Open Web Text)

Max Activating Token Index: 618

Text #6

Max Range: 5.9993. Min Range: -5.9993

Max Act: 5.8612. Min Act: -0.1700

Data Index: 5975753 (Open Web Text)

Max Activating Token Index: 669

Text #7

Max Range: 5.9993. Min Range: -5.9993

Max Act: 5.9133. Min Act: -0.1700

Data Index: 5498860 (Open Web Text)

Max Activating Token Index: 180

Text #8

Max Range: 5.9993. Min Range: -5.9993

Max Act: 5.8604. Min Act: -0.1700

Data Index: 3009231 (Open Web Text)

Max Activating Token Index: 342

Text #9

Max Range: 5.9993. Min Range: -5.9993

Max Act: 5.8446. Min Act: -0.1700

Data Index: 3369138 (Open Web Text)

Max Activating Token Index: 619

Text #10

Max Range: 5.9993. Min Range: -5.9993

Max Act: 5.8711. Min Act: -0.1700

Data Index: 4685528 (Open Web Text)

Max Activating Token Index: 226

Text #11

Max Range: 5.9993. Min Range: -5.9993

Max Act: 5.8528. Min Act: -0.1700

Data Index: 3614611 (Open Web Text)

Max Activating Token Index: 986

Text #12

Max Range: 5.9993. Min Range: -5.9993

Max Act: 5.8288. Min Act: -0.1700

Data Index: 7149464 (Open Web Text)

Max Activating Token Index: 355

Text #13

Max Range: 5.9993. Min Range: -5.9993

Max Act: 5.8347. Min Act: -0.1700

Data Index: 2541600 (Open Web Text)

Max Activating Token Index: 438

Text #14

Max Range: 5.9993. Min Range: -5.9993

Max Act: 5.8345. Min Act: -0.1700

Data Index: 1339501 (Open Web Text)

Max Activating Token Index: 840

Text #15

Max Range: 5.9993. Min Range: -5.9993

Max Act: 5.8514. Min Act: -0.1700

Data Index: 4540239 (Open Web Text)

Max Activating Token Index: 434

Text #16

Max Range: 5.9993. Min Range: -5.9993

Max Act: 5.8208. Min Act: -0.1700

Data Index: 6801228 (Open Web Text)

Max Activating Token Index: 273

Text #17

Max Range: 5.9993. Min Range: -5.9993

Max Act: 5.7914. Min Act: -0.1700

Data Index: 1976495 (Open Web Text)

Max Activating Token Index: 577

Text #18

Max Range: 5.9993. Min Range: -5.9993

Max Act: 5.7799. Min Act: -0.1700

Data Index: 218842 (Open Web Text)

Max Activating Token Index: 949

Text #19

Max Range: 5.9993. Min Range: -5.9993

Max Act: 5.7709. Min Act: -0.1700

Data Index: 6079954 (Open Web Text)

Max Activating Token Index: 431