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

Dataset: Open Web Text

Neuron 2790 in Layer 0

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: 2.5308. Min Range: -2.5308

Max Act: 2.5308. Min Act: -0.1700

Data Index: 6325185 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.4809. Min Act: -0.1700

Data Index: 3997264 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.4670. Min Act: -0.1700

Data Index: 5842289 (Open Web Text)

Max Activating Token Index: 16

Text #3

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.4687. Min Act: -0.1700

Data Index: 5591242 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.4622. Min Act: -0.1700

Data Index: 1103379 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.4487. Min Act: -0.1700

Data Index: 6441202 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.4604. Min Act: -0.1700

Data Index: 3665501 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.4422. Min Act: -0.1700

Data Index: 1555615 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.4337. Min Act: -0.1700

Data Index: 4600781 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.4336. Min Act: -0.1700

Data Index: 1967283 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.4359. Min Act: -0.1700

Data Index: 7045721 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.4443. Min Act: -0.1700

Data Index: 6487848 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.4325. Min Act: -0.1700

Data Index: 3521927 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.4130. Min Act: -0.1700

Data Index: 7156939 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.4212. Min Act: -0.1700

Data Index: 5329598 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.4160. Min Act: -0.1700

Data Index: 7553390 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.4321. Min Act: -0.1700

Data Index: 2017421 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.4214. Min Act: -0.1700

Data Index: 2642508 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.4230. Min Act: -0.1700

Data Index: 3445203 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 2.5308. Min Range: -2.5308

Max Act: 2.4103. Min Act: -0.1700

Data Index: 2347997 (Open Web Text)

Max Activating Token Index: 8