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

Dataset: Open Web Text

Neuron 393 in Layer 4

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: 3.3894. Min Range: -3.3894

Max Act: 3.3836. Min Act: -0.1700

Data Index: 1508947 (Open Web Text)

Max Activating Token Index: 601

Text #1

Max Range: 3.3894. Min Range: -3.3894

Max Act: 3.3670. Min Act: -0.1700

Data Index: 7220391 (Open Web Text)

Max Activating Token Index: 621

Text #2

Max Range: 3.3894. Min Range: -3.3894

Max Act: 3.3894. Min Act: -0.1700

Data Index: 6839051 (Open Web Text)

Max Activating Token Index: 443

Text #3

Max Range: 3.3894. Min Range: -3.3894

Max Act: 3.3542. Min Act: -0.1700

Data Index: 7512607 (Open Web Text)

Max Activating Token Index: 525

Text #4

Max Range: 3.3894. Min Range: -3.3894

Max Act: 3.3487. Min Act: -0.1700

Data Index: 2314813 (Open Web Text)

Max Activating Token Index: 962

Text #5

Max Range: 3.3894. Min Range: -3.3894

Max Act: 3.3346. Min Act: -0.1700

Data Index: 7977658 (Open Web Text)

Max Activating Token Index: 111

Text #6

Max Range: 3.3894. Min Range: -3.3894

Max Act: 3.3373. Min Act: -0.1700

Data Index: 2042051 (Open Web Text)

Max Activating Token Index: 739

Text #7

Max Range: 3.3894. Min Range: -3.3894

Max Act: 3.3365. Min Act: -0.1700

Data Index: 2474752 (Open Web Text)

Max Activating Token Index: 491

Text #8

Max Range: 3.3894. Min Range: -3.3894

Max Act: 3.3197. Min Act: -0.1700

Data Index: 8643108 (Open Web Text)

Max Activating Token Index: 125

Text #9

Max Range: 3.3894. Min Range: -3.3894

Max Act: 3.3261. Min Act: -0.1700

Data Index: 3854549 (Open Web Text)

Max Activating Token Index: 459

Text #10

Max Range: 3.3894. Min Range: -3.3894

Max Act: 3.3224. Min Act: -0.1700

Data Index: 2045113 (Open Web Text)

Max Activating Token Index: 967

Text #11

Max Range: 3.3894. Min Range: -3.3894

Max Act: 3.3138. Min Act: -0.1700

Data Index: 8070294 (Open Web Text)

Max Activating Token Index: 60

Text #12

Max Range: 3.3894. Min Range: -3.3894

Max Act: 3.3147. Min Act: -0.1700

Data Index: 1589993 (Open Web Text)

Max Activating Token Index: 1013

Text #13

Max Range: 3.3894. Min Range: -3.3894

Max Act: 3.3005. Min Act: -0.1700

Data Index: 8391663 (Open Web Text)

Max Activating Token Index: 832

Text #14

Max Range: 3.3894. Min Range: -3.3894

Max Act: 3.3093. Min Act: -0.1700

Data Index: 8755580 (Open Web Text)

Max Activating Token Index: 625

Text #15

Max Range: 3.3894. Min Range: -3.3894

Max Act: 3.2849. Min Act: -0.1700

Data Index: 7758947 (Open Web Text)

Max Activating Token Index: 419

Text #16

Max Range: 3.3894. Min Range: -3.3894

Max Act: 3.2888. Min Act: -0.1700

Data Index: 2367567 (Open Web Text)

Max Activating Token Index: 153

Text #17

Max Range: 3.3894. Min Range: -3.3894

Max Act: 3.2968. Min Act: -0.1700

Data Index: 4215763 (Open Web Text)

Max Activating Token Index: 519

Text #18

Max Range: 3.3894. Min Range: -3.3894

Max Act: 3.3311. Min Act: -0.1700

Data Index: 1381380 (Open Web Text)

Max Activating Token Index: 603

Text #19

Max Range: 3.3894. Min Range: -3.3894

Max Act: 3.2348. Min Act: -0.1700

Data Index: 8383270 (Open Web Text)

Max Activating Token Index: 965