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

Dataset: Open Web Text

Neuron 1036 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: 4.4515. Min Range: -4.4515

Max Act: 4.4515. Min Act: -0.1700

Data Index: 3951051 (Open Web Text)

Max Activating Token Index: 829

Text #1

Max Range: 4.4515. Min Range: -4.4515

Max Act: 4.3970. Min Act: -0.1700

Data Index: 2816628 (Open Web Text)

Max Activating Token Index: 374

Text #2

Max Range: 4.4515. Min Range: -4.4515

Max Act: 4.3537. Min Act: -0.1700

Data Index: 8277467 (Open Web Text)

Max Activating Token Index: 504

Text #3

Max Range: 4.4515. Min Range: -4.4515

Max Act: 4.3459. Min Act: -0.1700

Data Index: 1585704 (Open Web Text)

Max Activating Token Index: 274

Text #4

Max Range: 4.4515. Min Range: -4.4515

Max Act: 4.3652. Min Act: -0.1700

Data Index: 2905497 (Open Web Text)

Max Activating Token Index: 666

Text #5

Max Range: 4.4515. Min Range: -4.4515

Max Act: 4.3041. Min Act: -0.1700

Data Index: 7897655 (Open Web Text)

Max Activating Token Index: 278

Text #6

Max Range: 4.4515. Min Range: -4.4515

Max Act: 4.3207. Min Act: -0.1700

Data Index: 1603446 (Open Web Text)

Max Activating Token Index: 571

Text #7

Max Range: 4.4515. Min Range: -4.4515

Max Act: 4.3102. Min Act: -0.1700

Data Index: 2690520 (Open Web Text)

Max Activating Token Index: 254

Text #8

Max Range: 4.4515. Min Range: -4.4515

Max Act: 4.2788. Min Act: -0.1700

Data Index: 8321324 (Open Web Text)

Max Activating Token Index: 690

Text #9

Max Range: 4.4515. Min Range: -4.4515

Max Act: 4.3486. Min Act: -0.1700

Data Index: 3144360 (Open Web Text)

Max Activating Token Index: 705

Text #10

Max Range: 4.4515. Min Range: -4.4515

Max Act: 4.2939. Min Act: -0.1700

Data Index: 7874208 (Open Web Text)

Max Activating Token Index: 564

Text #11

Max Range: 4.4515. Min Range: -4.4515

Max Act: 4.3457. Min Act: -0.1700

Data Index: 5098918 (Open Web Text)

Max Activating Token Index: 470

Text #12

Max Range: 4.4515. Min Range: -4.4515

Max Act: 4.2882. Min Act: -0.1700

Data Index: 4037384 (Open Web Text)

Max Activating Token Index: 86

Text #13

Max Range: 4.4515. Min Range: -4.4515

Max Act: 4.2317. Min Act: -0.1700

Data Index: 2029650 (Open Web Text)

Max Activating Token Index: 377

Text #14

Max Range: 4.4515. Min Range: -4.4515

Max Act: 4.2424. Min Act: -0.1700

Data Index: 6617255 (Open Web Text)

Max Activating Token Index: 830

Text #15

Max Range: 4.4515. Min Range: -4.4515

Max Act: 4.2868. Min Act: -0.1700

Data Index: 6288222 (Open Web Text)

Max Activating Token Index: 150

Text #16

Max Range: 4.4515. Min Range: -4.4515

Max Act: 4.2299. Min Act: -0.1700

Data Index: 3561182 (Open Web Text)

Max Activating Token Index: 319

Text #17

Max Range: 4.4515. Min Range: -4.4515

Max Act: 4.2178. Min Act: -0.1700

Data Index: 2862291 (Open Web Text)

Max Activating Token Index: 276

Text #18

Max Range: 4.4515. Min Range: -4.4515

Max Act: 4.2244. Min Act: -0.1700

Data Index: 2988733 (Open Web Text)

Max Activating Token Index: 458

Text #19

Max Range: 4.4515. Min Range: -4.4515

Max Act: 4.2395. Min Act: -0.1700

Data Index: 3103029 (Open Web Text)

Max Activating Token Index: 429