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

Dataset: Open Web Text

Neuron 1650 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: 4.5217. Min Range: -4.5217

Max Act: 4.5217. Min Act: -0.1700

Data Index: 7819659 (Open Web Text)

Max Activating Token Index: 63

Text #1

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.4960. Min Act: -0.1700

Data Index: 5812169 (Open Web Text)

Max Activating Token Index: 447

Text #2

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.4560. Min Act: -0.1700

Data Index: 1612278 (Open Web Text)

Max Activating Token Index: 300

Text #3

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.4687. Min Act: -0.1700

Data Index: 5339432 (Open Web Text)

Max Activating Token Index: 386

Text #4

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.4741. Min Act: -0.1700

Data Index: 5292497 (Open Web Text)

Max Activating Token Index: 467

Text #5

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.4554. Min Act: -0.1700

Data Index: 1517673 (Open Web Text)

Max Activating Token Index: 540

Text #6

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.4946. Min Act: -0.1700

Data Index: 1238627 (Open Web Text)

Max Activating Token Index: 444

Text #7

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.4545. Min Act: -0.1700

Data Index: 5316628 (Open Web Text)

Max Activating Token Index: 479

Text #8

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.4449. Min Act: -0.1700

Data Index: 7935876 (Open Web Text)

Max Activating Token Index: 637

Text #9

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.4442. Min Act: -0.1700

Data Index: 5454675 (Open Web Text)

Max Activating Token Index: 760

Text #10

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.4608. Min Act: -0.1700

Data Index: 6300230 (Open Web Text)

Max Activating Token Index: 637

Text #11

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.4320. Min Act: -0.1700

Data Index: 5024907 (Open Web Text)

Max Activating Token Index: 344

Text #12

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.4253. Min Act: -0.1700

Data Index: 2593764 (Open Web Text)

Max Activating Token Index: 390

Text #13

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.4418. Min Act: -0.1700

Data Index: 989587 (Open Web Text)

Max Activating Token Index: 286

Text #14

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.3866. Min Act: -0.1700

Data Index: 6820224 (Open Web Text)

Max Activating Token Index: 487

Text #15

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.4185. Min Act: -0.1700

Data Index: 7411831 (Open Web Text)

Max Activating Token Index: 200

Text #16

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.4010. Min Act: -0.1700

Data Index: 8796143 (Open Web Text)

Max Activating Token Index: 545

Text #17

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.4147. Min Act: -0.1700

Data Index: 5697230 (Open Web Text)

Max Activating Token Index: 316

Text #18

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.3989. Min Act: -0.1700

Data Index: 8343113 (Open Web Text)

Max Activating Token Index: 685

Text #19

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.3798. Min Act: -0.1700

Data Index: 1249724 (Open Web Text)

Max Activating Token Index: 1021