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

Dataset: Open Web Text

Neuron 2141 in Layer 2

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: 4.6341. Min Range: -4.6341

Max Act: 4.6341. Min Act: -0.1700

Data Index: 8636724 (Open Web Text)

Max Activating Token Index: 270

Text #1

Max Range: 4.6341. Min Range: -4.6341

Max Act: 4.5913. Min Act: -0.1700

Data Index: 5220877 (Open Web Text)

Max Activating Token Index: 727

Text #2

Max Range: 4.6341. Min Range: -4.6341

Max Act: 4.5380. Min Act: -0.1700

Data Index: 1519655 (Open Web Text)

Max Activating Token Index: 788

Text #3

Max Range: 4.6341. Min Range: -4.6341

Max Act: 4.5588. Min Act: -0.1700

Data Index: 4066244 (Open Web Text)

Max Activating Token Index: 216

Text #4

Max Range: 4.6341. Min Range: -4.6341

Max Act: 4.4727. Min Act: -0.1700

Data Index: 1519653 (Open Web Text)

Max Activating Token Index: 799

Text #5

Max Range: 4.6341. Min Range: -4.6341

Max Act: 4.5123. Min Act: -0.1700

Data Index: 8636717 (Open Web Text)

Max Activating Token Index: 386

Text #6

Max Range: 4.6341. Min Range: -4.6341

Max Act: 4.4752. Min Act: -0.1700

Data Index: 8660214 (Open Web Text)

Max Activating Token Index: 261

Text #7

Max Range: 4.6341. Min Range: -4.6341

Max Act: 4.4771. Min Act: -0.1700

Data Index: 7742019 (Open Web Text)

Max Activating Token Index: 554

Text #8

Max Range: 4.6341. Min Range: -4.6341

Max Act: 4.4223. Min Act: -0.1700

Data Index: 1519654 (Open Web Text)

Max Activating Token Index: 960

Text #9

Max Range: 4.6341. Min Range: -4.6341

Max Act: 4.4269. Min Act: -0.1700

Data Index: 2827612 (Open Web Text)

Max Activating Token Index: 860

Text #10

Max Range: 4.6341. Min Range: -4.6341

Max Act: 4.4268. Min Act: -0.1700

Data Index: 3929332 (Open Web Text)

Max Activating Token Index: 275

Text #11

Max Range: 4.6341. Min Range: -4.6341

Max Act: 4.3988. Min Act: -0.1700

Data Index: 7471550 (Open Web Text)

Max Activating Token Index: 245

Text #12

Max Range: 4.6341. Min Range: -4.6341

Max Act: 4.3986. Min Act: -0.1700

Data Index: 8239530 (Open Web Text)

Max Activating Token Index: 537

Text #13

Max Range: 4.6341. Min Range: -4.6341

Max Act: 4.3878. Min Act: -0.1700

Data Index: 1907512 (Open Web Text)

Max Activating Token Index: 646

Text #14

Max Range: 4.6341. Min Range: -4.6341

Max Act: 4.3612. Min Act: -0.1700

Data Index: 6392005 (Open Web Text)

Max Activating Token Index: 142

Text #15

Max Range: 4.6341. Min Range: -4.6341

Max Act: 4.3842. Min Act: -0.1700

Data Index: 169305 (Open Web Text)

Max Activating Token Index: 301

Text #16

Max Range: 4.6341. Min Range: -4.6341

Max Act: 4.3848. Min Act: -0.1700

Data Index: 4569355 (Open Web Text)

Max Activating Token Index: 95

Text #17

Max Range: 4.6341. Min Range: -4.6341

Max Act: 4.3788. Min Act: -0.1700

Data Index: 3644236 (Open Web Text)

Max Activating Token Index: 132

Text #18

Max Range: 4.6341. Min Range: -4.6341

Max Act: 4.3352. Min Act: -0.1700

Data Index: 3712801 (Open Web Text)

Max Activating Token Index: 770

Text #19

Max Range: 4.6341. Min Range: -4.6341

Max Act: 4.3479. Min Act: -0.1700

Data Index: 8636720 (Open Web Text)

Max Activating Token Index: 368