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

Dataset: Open Web Text

Neuron 385 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: 4.6265. Min Range: -4.6265

Max Act: 4.6265. Min Act: -0.1700

Data Index: 7817910 (Open Web Text)

Max Activating Token Index: 310

Text #1

Max Range: 4.6265. Min Range: -4.6265

Max Act: 4.5779. Min Act: -0.1700

Data Index: 2452092 (Open Web Text)

Max Activating Token Index: 84

Text #2

Max Range: 4.6265. Min Range: -4.6265

Max Act: 4.5370. Min Act: -0.1700

Data Index: 1612422 (Open Web Text)

Max Activating Token Index: 72

Text #3

Max Range: 4.6265. Min Range: -4.6265

Max Act: 4.5624. Min Act: -0.1700

Data Index: 2051712 (Open Web Text)

Max Activating Token Index: 78

Text #4

Max Range: 4.6265. Min Range: -4.6265

Max Act: 4.4003. Min Act: -0.1700

Data Index: 6379896 (Open Web Text)

Max Activating Token Index: 329

Text #5

Max Range: 4.6265. Min Range: -4.6265

Max Act: 4.3434. Min Act: -0.1700

Data Index: 8641620 (Open Web Text)

Max Activating Token Index: 53

Text #6

Max Range: 4.6265. Min Range: -4.6265

Max Act: 4.3175. Min Act: -0.1700

Data Index: 2518434 (Open Web Text)

Max Activating Token Index: 359

Text #7

Max Range: 4.6265. Min Range: -4.6265

Max Act: 4.3194. Min Act: -0.1700

Data Index: 8721496 (Open Web Text)

Max Activating Token Index: 280

Text #8

Max Range: 4.6265. Min Range: -4.6265

Max Act: 4.2775. Min Act: -0.1700

Data Index: 1583252 (Open Web Text)

Max Activating Token Index: 961

Text #9

Max Range: 4.6265. Min Range: -4.6265

Max Act: 4.2729. Min Act: -0.1700

Data Index: 722755 (Open Web Text)

Max Activating Token Index: 541

Text #10

Max Range: 4.6265. Min Range: -4.6265

Max Act: 4.2636. Min Act: -0.1700

Data Index: 8647776 (Open Web Text)

Max Activating Token Index: 628

Text #11

Max Range: 4.6265. Min Range: -4.6265

Max Act: 4.2670. Min Act: -0.1700

Data Index: 8464527 (Open Web Text)

Max Activating Token Index: 527

Text #12

Max Range: 4.6265. Min Range: -4.6265

Max Act: 4.2172. Min Act: -0.1700

Data Index: 6468561 (Open Web Text)

Max Activating Token Index: 314

Text #13

Max Range: 4.6265. Min Range: -4.6265

Max Act: 4.2147. Min Act: -0.1700

Data Index: 2355377 (Open Web Text)

Max Activating Token Index: 1014

Text #14

Max Range: 4.6265. Min Range: -4.6265

Max Act: 4.2314. Min Act: -0.1700

Data Index: 3388152 (Open Web Text)

Max Activating Token Index: 337

Text #15

Max Range: 4.6265. Min Range: -4.6265

Max Act: 4.2140. Min Act: -0.1700

Data Index: 403291 (Open Web Text)

Max Activating Token Index: 343

Text #16

Max Range: 4.6265. Min Range: -4.6265

Max Act: 4.1827. Min Act: -0.1700

Data Index: 2362293 (Open Web Text)

Max Activating Token Index: 246

Text #17

Max Range: 4.6265. Min Range: -4.6265

Max Act: 4.2057. Min Act: -0.1700

Data Index: 4322681 (Open Web Text)

Max Activating Token Index: 514

Text #18

Max Range: 4.6265. Min Range: -4.6265

Max Act: 4.1871. Min Act: -0.1700

Data Index: 4430165 (Open Web Text)

Max Activating Token Index: 91

Text #19

Max Range: 4.6265. Min Range: -4.6265

Max Act: 4.1862. Min Act: -0.1700

Data Index: 4982914 (Open Web Text)

Max Activating Token Index: 202