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

Dataset: Open Web Text

Neuron 1892 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: 3.8853. Min Range: -3.8853

Max Act: 3.8853. Min Act: -0.1700

Data Index: 8197003 (Open Web Text)

Max Activating Token Index: 169

Text #1

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.8161. Min Act: -0.1700

Data Index: 4922998 (Open Web Text)

Max Activating Token Index: 960

Text #2

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.8171. Min Act: -0.1700

Data Index: 2596547 (Open Web Text)

Max Activating Token Index: 765

Text #3

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.8164. Min Act: -0.1700

Data Index: 5689387 (Open Web Text)

Max Activating Token Index: 164

Text #4

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.8090. Min Act: -0.1700

Data Index: 4305919 (Open Web Text)

Max Activating Token Index: 418

Text #5

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.7685. Min Act: -0.1700

Data Index: 4989326 (Open Web Text)

Max Activating Token Index: 330

Text #6

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.7865. Min Act: -0.1700

Data Index: 3087975 (Open Web Text)

Max Activating Token Index: 332

Text #7

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.7829. Min Act: -0.1700

Data Index: 7323194 (Open Web Text)

Max Activating Token Index: 869

Text #8

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.7857. Min Act: -0.1700

Data Index: 2723862 (Open Web Text)

Max Activating Token Index: 636

Text #9

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.7545. Min Act: -0.1700

Data Index: 7380503 (Open Web Text)

Max Activating Token Index: 62

Text #10

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.7409. Min Act: -0.1700

Data Index: 318807 (Open Web Text)

Max Activating Token Index: 444

Text #11

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.7357. Min Act: -0.1700

Data Index: 5153946 (Open Web Text)

Max Activating Token Index: 284

Text #12

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.7450. Min Act: -0.1700

Data Index: 346926 (Open Web Text)

Max Activating Token Index: 468

Text #13

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.7326. Min Act: -0.1700

Data Index: 2980589 (Open Web Text)

Max Activating Token Index: 315

Text #14

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.7378. Min Act: -0.1700

Data Index: 5684827 (Open Web Text)

Max Activating Token Index: 463

Text #15

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.7107. Min Act: -0.1700

Data Index: 3458644 (Open Web Text)

Max Activating Token Index: 665

Text #16

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.6943. Min Act: -0.1700

Data Index: 598020 (Open Web Text)

Max Activating Token Index: 624

Text #17

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.7269. Min Act: -0.1700

Data Index: 5295959 (Open Web Text)

Max Activating Token Index: 596

Text #18

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.6998. Min Act: -0.1700

Data Index: 4938558 (Open Web Text)

Max Activating Token Index: 502

Text #19

Max Range: 3.8853. Min Range: -3.8853

Max Act: 3.6743. Min Act: -0.1700

Data Index: 1183357 (Open Web Text)

Max Activating Token Index: 411