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

Dataset: Open Web Text

Neuron 1957 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: 4.9242. Min Range: -4.9242

Max Act: 4.9242. Min Act: -0.1700

Data Index: 3764323 (Open Web Text)

Max Activating Token Index: 285

Text #1

Max Range: 4.9242. Min Range: -4.9242

Max Act: 4.8637. Min Act: -0.1700

Data Index: 5612600 (Open Web Text)

Max Activating Token Index: 219

Text #2

Max Range: 4.9242. Min Range: -4.9242

Max Act: 4.8356. Min Act: -0.1700

Data Index: 7696239 (Open Web Text)

Max Activating Token Index: 962

Text #3

Max Range: 4.9242. Min Range: -4.9242

Max Act: 4.8729. Min Act: -0.1700

Data Index: 4316454 (Open Web Text)

Max Activating Token Index: 520

Text #4

Max Range: 4.9242. Min Range: -4.9242

Max Act: 4.8414. Min Act: -0.1700

Data Index: 8213637 (Open Web Text)

Max Activating Token Index: 375

Text #5

Max Range: 4.9242. Min Range: -4.9242

Max Act: 4.8485. Min Act: -0.1700

Data Index: 7593403 (Open Web Text)

Max Activating Token Index: 755

Text #6

Max Range: 4.9242. Min Range: -4.9242

Max Act: 4.8211. Min Act: -0.1700

Data Index: 629934 (Open Web Text)

Max Activating Token Index: 722

Text #7

Max Range: 4.9242. Min Range: -4.9242

Max Act: 4.8247. Min Act: -0.1700

Data Index: 6138654 (Open Web Text)

Max Activating Token Index: 623

Text #8

Max Range: 4.9242. Min Range: -4.9242

Max Act: 4.7624. Min Act: -0.1700

Data Index: 6304703 (Open Web Text)

Max Activating Token Index: 443

Text #9

Max Range: 4.9242. Min Range: -4.9242

Max Act: 4.7961. Min Act: -0.1700

Data Index: 3260532 (Open Web Text)

Max Activating Token Index: 918

Text #10

Max Range: 4.9242. Min Range: -4.9242

Max Act: 4.7693. Min Act: -0.1700

Data Index: 2252833 (Open Web Text)

Max Activating Token Index: 611

Text #11

Max Range: 4.9242. Min Range: -4.9242

Max Act: 4.7659. Min Act: -0.1700

Data Index: 5899296 (Open Web Text)

Max Activating Token Index: 399

Text #12

Max Range: 4.9242. Min Range: -4.9242

Max Act: 4.7448. Min Act: -0.1700

Data Index: 7463275 (Open Web Text)

Max Activating Token Index: 705

Text #13

Max Range: 4.9242. Min Range: -4.9242

Max Act: 4.7696. Min Act: -0.1700

Data Index: 6000582 (Open Web Text)

Max Activating Token Index: 774

Text #14

Max Range: 4.9242. Min Range: -4.9242

Max Act: 4.7610. Min Act: -0.1700

Data Index: 8213638 (Open Web Text)

Max Activating Token Index: 730

Text #15

Max Range: 4.9242. Min Range: -4.9242

Max Act: 4.7847. Min Act: -0.1700

Data Index: 3820067 (Open Web Text)

Max Activating Token Index: 721

Text #16

Max Range: 4.9242. Min Range: -4.9242

Max Act: 4.7881. Min Act: -0.1700

Data Index: 348712 (Open Web Text)

Max Activating Token Index: 524

Text #17

Max Range: 4.9242. Min Range: -4.9242

Max Act: 4.7475. Min Act: -0.1700

Data Index: 1390180 (Open Web Text)

Max Activating Token Index: 739

Text #18

Max Range: 4.9242. Min Range: -4.9242

Max Act: 4.7394. Min Act: -0.1700

Data Index: 8124676 (Open Web Text)

Max Activating Token Index: 479

Text #19

Max Range: 4.9242. Min Range: -4.9242

Max Act: 4.7231. Min Act: -0.1700

Data Index: 6415751 (Open Web Text)

Max Activating Token Index: 869