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

Dataset: Open Web Text

Neuron 1364 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: 5.4097. Min Range: -5.4097

Max Act: 5.4097. Min Act: -0.1700

Data Index: 1108530 (Open Web Text)

Max Activating Token Index: 453

Text #1

Max Range: 5.4097. Min Range: -5.4097

Max Act: 5.3571. Min Act: -0.1700

Data Index: 7680080 (Open Web Text)

Max Activating Token Index: 582

Text #2

Max Range: 5.4097. Min Range: -5.4097

Max Act: 5.3119. Min Act: -0.1700

Data Index: 3285192 (Open Web Text)

Max Activating Token Index: 421

Text #3

Max Range: 5.4097. Min Range: -5.4097

Max Act: 5.3436. Min Act: -0.1700

Data Index: 4355491 (Open Web Text)

Max Activating Token Index: 715

Text #4

Max Range: 5.4097. Min Range: -5.4097

Max Act: 5.3076. Min Act: -0.1700

Data Index: 1019224 (Open Web Text)

Max Activating Token Index: 362

Text #5

Max Range: 5.4097. Min Range: -5.4097

Max Act: 5.3013. Min Act: -0.1700

Data Index: 4147072 (Open Web Text)

Max Activating Token Index: 15

Text #6

Max Range: 5.4097. Min Range: -5.4097

Max Act: 5.3078. Min Act: -0.1700

Data Index: 6324719 (Open Web Text)

Max Activating Token Index: 57

Text #7

Max Range: 5.4097. Min Range: -5.4097

Max Act: 5.3142. Min Act: -0.1700

Data Index: 6459 (Open Web Text)

Max Activating Token Index: 803

Text #8

Max Range: 5.4097. Min Range: -5.4097

Max Act: 5.2987. Min Act: -0.1700

Data Index: 6512839 (Open Web Text)

Max Activating Token Index: 435

Text #9

Max Range: 5.4097. Min Range: -5.4097

Max Act: 5.2801. Min Act: -0.1700

Data Index: 4952418 (Open Web Text)

Max Activating Token Index: 664

Text #10

Max Range: 5.4097. Min Range: -5.4097

Max Act: 5.2990. Min Act: -0.1700

Data Index: 4127426 (Open Web Text)

Max Activating Token Index: 483

Text #11

Max Range: 5.4097. Min Range: -5.4097

Max Act: 5.2640. Min Act: -0.1700

Data Index: 5288846 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 5.4097. Min Range: -5.4097

Max Act: 5.2851. Min Act: -0.1700

Data Index: 6030980 (Open Web Text)

Max Activating Token Index: 396

Text #13

Max Range: 5.4097. Min Range: -5.4097

Max Act: 5.2427. Min Act: -0.1700

Data Index: 8683001 (Open Web Text)

Max Activating Token Index: 376

Text #14

Max Range: 5.4097. Min Range: -5.4097

Max Act: 5.2382. Min Act: -0.1700

Data Index: 8187119 (Open Web Text)

Max Activating Token Index: 163

Text #15

Max Range: 5.4097. Min Range: -5.4097

Max Act: 5.2402. Min Act: -0.1700

Data Index: 3187606 (Open Web Text)

Max Activating Token Index: 382

Text #16

Max Range: 5.4097. Min Range: -5.4097

Max Act: 5.2490. Min Act: -0.1700

Data Index: 3505102 (Open Web Text)

Max Activating Token Index: 226

Text #17

Max Range: 5.4097. Min Range: -5.4097

Max Act: 5.2363. Min Act: -0.1700

Data Index: 4865511 (Open Web Text)

Max Activating Token Index: 934

Text #18

Max Range: 5.4097. Min Range: -5.4097

Max Act: 5.2360. Min Act: -0.1700

Data Index: 6361204 (Open Web Text)

Max Activating Token Index: 393

Text #19

Max Range: 5.4097. Min Range: -5.4097

Max Act: 5.2596. Min Act: -0.1700

Data Index: 435803 (Open Web Text)

Max Activating Token Index: 886