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

Dataset: Open Web Text

Neuron 623 in Layer 5

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: 3.7291. Min Range: -3.7291

Max Act: 3.7291. Min Act: -0.1700

Data Index: 5057520 (Open Web Text)

Max Activating Token Index: 342

Text #1

Max Range: 3.7291. Min Range: -3.7291

Max Act: 3.6623. Min Act: -0.1700

Data Index: 5936090 (Open Web Text)

Max Activating Token Index: 356

Text #2

Max Range: 3.7291. Min Range: -3.7291

Max Act: 3.6532. Min Act: -0.1700

Data Index: 5562379 (Open Web Text)

Max Activating Token Index: 632

Text #3

Max Range: 3.7291. Min Range: -3.7291

Max Act: 3.6319. Min Act: -0.1700

Data Index: 5698856 (Open Web Text)

Max Activating Token Index: 256

Text #4

Max Range: 3.7291. Min Range: -3.7291

Max Act: 3.6177. Min Act: -0.1700

Data Index: 7611007 (Open Web Text)

Max Activating Token Index: 228

Text #5

Max Range: 3.7291. Min Range: -3.7291

Max Act: 3.6238. Min Act: -0.1700

Data Index: 5149363 (Open Web Text)

Max Activating Token Index: 421

Text #6

Max Range: 3.7291. Min Range: -3.7291

Max Act: 3.6161. Min Act: -0.1700

Data Index: 4658490 (Open Web Text)

Max Activating Token Index: 676

Text #7

Max Range: 3.7291. Min Range: -3.7291

Max Act: 3.6105. Min Act: -0.1700

Data Index: 993788 (Open Web Text)

Max Activating Token Index: 128

Text #8

Max Range: 3.7291. Min Range: -3.7291

Max Act: 3.5892. Min Act: -0.1700

Data Index: 6053053 (Open Web Text)

Max Activating Token Index: 843

Text #9

Max Range: 3.7291. Min Range: -3.7291

Max Act: 3.5433. Min Act: -0.1700

Data Index: 4736167 (Open Web Text)

Max Activating Token Index: 438

Text #10

Max Range: 3.7291. Min Range: -3.7291

Max Act: 3.5517. Min Act: -0.1700

Data Index: 5250158 (Open Web Text)

Max Activating Token Index: 771

Text #11

Max Range: 3.7291. Min Range: -3.7291

Max Act: 3.5364. Min Act: -0.1700

Data Index: 7884749 (Open Web Text)

Max Activating Token Index: 383

Text #12

Max Range: 3.7291. Min Range: -3.7291

Max Act: 3.5201. Min Act: -0.1700

Data Index: 2666072 (Open Web Text)

Max Activating Token Index: 211

Text #13

Max Range: 3.7291. Min Range: -3.7291

Max Act: 3.5491. Min Act: -0.1700

Data Index: 1654205 (Open Web Text)

Max Activating Token Index: 24

Text #14

Max Range: 3.7291. Min Range: -3.7291

Max Act: 3.5328. Min Act: -0.1700

Data Index: 8617528 (Open Web Text)

Max Activating Token Index: 634

Text #15

Max Range: 3.7291. Min Range: -3.7291

Max Act: 3.5279. Min Act: -0.1700

Data Index: 508882 (Open Web Text)

Max Activating Token Index: 577

Text #16

Max Range: 3.7291. Min Range: -3.7291

Max Act: 3.5054. Min Act: -0.1700

Data Index: 3205052 (Open Web Text)

Max Activating Token Index: 656

Text #17

Max Range: 3.7291. Min Range: -3.7291

Max Act: 3.5039. Min Act: -0.1700

Data Index: 5947111 (Open Web Text)

Max Activating Token Index: 301

Text #18

Max Range: 3.7291. Min Range: -3.7291

Max Act: 3.5154. Min Act: -0.1700

Data Index: 3973842 (Open Web Text)

Max Activating Token Index: 428

Text #19

Max Range: 3.7291. Min Range: -3.7291

Max Act: 3.4893. Min Act: -0.1700

Data Index: 1684160 (Open Web Text)

Max Activating Token Index: 425