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

Dataset: Open Web Text

Neuron 2598 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: 3.7455. Min Range: -3.7455

Max Act: 3.7455. Min Act: -0.1700

Data Index: 7134265 (Open Web Text)

Max Activating Token Index: 891

Text #1

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.7259. Min Act: -0.1700

Data Index: 632605 (Open Web Text)

Max Activating Token Index: 192

Text #2

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.6329. Min Act: -0.1700

Data Index: 6050998 (Open Web Text)

Max Activating Token Index: 905

Text #3

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.6356. Min Act: -0.1700

Data Index: 7592351 (Open Web Text)

Max Activating Token Index: 336

Text #4

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5318. Min Act: -0.1700

Data Index: 1662131 (Open Web Text)

Max Activating Token Index: 632

Text #5

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5436. Min Act: -0.1700

Data Index: 8802444 (Open Web Text)

Max Activating Token Index: 688

Text #6

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5337. Min Act: -0.1700

Data Index: 1923043 (Open Web Text)

Max Activating Token Index: 462

Text #7

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5393. Min Act: -0.1700

Data Index: 5781449 (Open Web Text)

Max Activating Token Index: 505

Text #8

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5359. Min Act: -0.1700

Data Index: 7553086 (Open Web Text)

Max Activating Token Index: 219

Text #9

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.4916. Min Act: -0.1700

Data Index: 8502509 (Open Web Text)

Max Activating Token Index: 747

Text #10

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5159. Min Act: -0.1700

Data Index: 2274112 (Open Web Text)

Max Activating Token Index: 861

Text #11

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.4980. Min Act: -0.1700

Data Index: 4672385 (Open Web Text)

Max Activating Token Index: 311

Text #12

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5235. Min Act: -0.1700

Data Index: 4351221 (Open Web Text)

Max Activating Token Index: 456

Text #13

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.4996. Min Act: -0.1700

Data Index: 5806646 (Open Web Text)

Max Activating Token Index: 478

Text #14

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.4886. Min Act: -0.1700

Data Index: 4464876 (Open Web Text)

Max Activating Token Index: 923

Text #15

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.4987. Min Act: -0.1700

Data Index: 4351725 (Open Web Text)

Max Activating Token Index: 837

Text #16

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.4927. Min Act: -0.1700

Data Index: 8776185 (Open Web Text)

Max Activating Token Index: 529

Text #17

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.4785. Min Act: -0.1700

Data Index: 7994509 (Open Web Text)

Max Activating Token Index: 71

Text #18

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.4788. Min Act: -0.1700

Data Index: 6862102 (Open Web Text)

Max Activating Token Index: 671

Text #19

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.4385. Min Act: -0.1700

Data Index: 4233540 (Open Web Text)

Max Activating Token Index: 661