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

Dataset: Open Web Text

Neuron 1916 in Layer 1

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: 4.4192. Min Range: -4.4192

Max Act: 4.4192. Min Act: -0.1700

Data Index: 3096927 (Open Web Text)

Max Activating Token Index: 479

Text #1

Max Range: 4.4192. Min Range: -4.4192

Max Act: 4.3457. Min Act: -0.1700

Data Index: 537839 (Open Web Text)

Max Activating Token Index: 281

Text #2

Max Range: 4.4192. Min Range: -4.4192

Max Act: 4.3257. Min Act: -0.1700

Data Index: 2920730 (Open Web Text)

Max Activating Token Index: 1015

Text #3

Max Range: 4.4192. Min Range: -4.4192

Max Act: 4.3042. Min Act: -0.1700

Data Index: 8346497 (Open Web Text)

Max Activating Token Index: 299

Text #4

Max Range: 4.4192. Min Range: -4.4192

Max Act: 4.3043. Min Act: -0.1700

Data Index: 416222 (Open Web Text)

Max Activating Token Index: 716

Text #5

Max Range: 4.4192. Min Range: -4.4192

Max Act: 4.2990. Min Act: -0.1700

Data Index: 7643078 (Open Web Text)

Max Activating Token Index: 389

Text #6

Max Range: 4.4192. Min Range: -4.4192

Max Act: 4.3090. Min Act: -0.1700

Data Index: 6947683 (Open Web Text)

Max Activating Token Index: 541

Text #7

Max Range: 4.4192. Min Range: -4.4192

Max Act: 4.2970. Min Act: -0.1700

Data Index: 3045168 (Open Web Text)

Max Activating Token Index: 973

Text #8

Max Range: 4.4192. Min Range: -4.4192

Max Act: 4.2920. Min Act: -0.1700

Data Index: 4798224 (Open Web Text)

Max Activating Token Index: 527

Text #9

Max Range: 4.4192. Min Range: -4.4192

Max Act: 4.2878. Min Act: -0.1700

Data Index: 2318903 (Open Web Text)

Max Activating Token Index: 632

Text #10

Max Range: 4.4192. Min Range: -4.4192

Max Act: 4.3026. Min Act: -0.1700

Data Index: 537835 (Open Web Text)

Max Activating Token Index: 612

Text #11

Max Range: 4.4192. Min Range: -4.4192

Max Act: 4.2755. Min Act: -0.1700

Data Index: 6487113 (Open Web Text)

Max Activating Token Index: 984

Text #12

Max Range: 4.4192. Min Range: -4.4192

Max Act: 4.2811. Min Act: -0.1700

Data Index: 37705 (Open Web Text)

Max Activating Token Index: 548

Text #13

Max Range: 4.4192. Min Range: -4.4192

Max Act: 4.2409. Min Act: -0.1700

Data Index: 1599069 (Open Web Text)

Max Activating Token Index: 831

Text #14

Max Range: 4.4192. Min Range: -4.4192

Max Act: 4.2452. Min Act: -0.1700

Data Index: 5008015 (Open Web Text)

Max Activating Token Index: 562

Text #15

Max Range: 4.4192. Min Range: -4.4192

Max Act: 4.2572. Min Act: -0.1700

Data Index: 1203896 (Open Web Text)

Max Activating Token Index: 334

Text #16

Max Range: 4.4192. Min Range: -4.4192

Max Act: 4.2502. Min Act: -0.1700

Data Index: 1241847 (Open Web Text)

Max Activating Token Index: 447

Text #17

Max Range: 4.4192. Min Range: -4.4192

Max Act: 4.2596. Min Act: -0.1700

Data Index: 5274541 (Open Web Text)

Max Activating Token Index: 857

Text #18

Max Range: 4.4192. Min Range: -4.4192

Max Act: 4.2623. Min Act: -0.1700

Data Index: 5934647 (Open Web Text)

Max Activating Token Index: 621

Text #19

Max Range: 4.4192. Min Range: -4.4192

Max Act: 4.2420. Min Act: -0.1700

Data Index: 6465449 (Open Web Text)

Max Activating Token Index: 427