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

Dataset: Open Web Text

Neuron 816 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: 4.1306. Min Range: -4.1306

Max Act: 4.1306. Min Act: -0.1700

Data Index: 8384935 (Open Web Text)

Max Activating Token Index: 530

Text #1

Max Range: 4.1306. Min Range: -4.1306

Max Act: 4.1188. Min Act: -0.1700

Data Index: 4338529 (Open Web Text)

Max Activating Token Index: 423

Text #2

Max Range: 4.1306. Min Range: -4.1306

Max Act: 4.0545. Min Act: -0.1700

Data Index: 8217973 (Open Web Text)

Max Activating Token Index: 819

Text #3

Max Range: 4.1306. Min Range: -4.1306

Max Act: 3.9565. Min Act: -0.1700

Data Index: 208986 (Open Web Text)

Max Activating Token Index: 612

Text #4

Max Range: 4.1306. Min Range: -4.1306

Max Act: 4.0472. Min Act: -0.1700

Data Index: 7310920 (Open Web Text)

Max Activating Token Index: 536

Text #5

Max Range: 4.1306. Min Range: -4.1306

Max Act: 3.9373. Min Act: -0.1700

Data Index: 7265578 (Open Web Text)

Max Activating Token Index: 407

Text #6

Max Range: 4.1306. Min Range: -4.1306

Max Act: 4.0198. Min Act: -0.1700

Data Index: 3975746 (Open Web Text)

Max Activating Token Index: 471

Text #7

Max Range: 4.1306. Min Range: -4.1306

Max Act: 3.9409. Min Act: -0.1700

Data Index: 5181924 (Open Web Text)

Max Activating Token Index: 678

Text #8

Max Range: 4.1306. Min Range: -4.1306

Max Act: 3.9331. Min Act: -0.1700

Data Index: 24110 (Open Web Text)

Max Activating Token Index: 564

Text #9

Max Range: 4.1306. Min Range: -4.1306

Max Act: 3.9561. Min Act: -0.1700

Data Index: 7513047 (Open Web Text)

Max Activating Token Index: 92

Text #10

Max Range: 4.1306. Min Range: -4.1306

Max Act: 3.9465. Min Act: -0.1700

Data Index: 8164328 (Open Web Text)

Max Activating Token Index: 158

Text #11

Max Range: 4.1306. Min Range: -4.1306

Max Act: 3.8965. Min Act: -0.1700

Data Index: 6430931 (Open Web Text)

Max Activating Token Index: 555

Text #12

Max Range: 4.1306. Min Range: -4.1306

Max Act: 3.8904. Min Act: -0.1700

Data Index: 229250 (Open Web Text)

Max Activating Token Index: 700

Text #13

Max Range: 4.1306. Min Range: -4.1306

Max Act: 3.8556. Min Act: -0.1700

Data Index: 3157030 (Open Web Text)

Max Activating Token Index: 371

Text #14

Max Range: 4.1306. Min Range: -4.1306

Max Act: 3.8485. Min Act: -0.1700

Data Index: 1059767 (Open Web Text)

Max Activating Token Index: 299

Text #15

Max Range: 4.1306. Min Range: -4.1306

Max Act: 3.9011. Min Act: -0.1700

Data Index: 2049106 (Open Web Text)

Max Activating Token Index: 769

Text #16

Max Range: 4.1306. Min Range: -4.1306

Max Act: 3.8704. Min Act: -0.1700

Data Index: 4065627 (Open Web Text)

Max Activating Token Index: 554

Text #17

Max Range: 4.1306. Min Range: -4.1306

Max Act: 3.8438. Min Act: -0.1700

Data Index: 6889489 (Open Web Text)

Max Activating Token Index: 856

Text #18

Max Range: 4.1306. Min Range: -4.1306

Max Act: 3.8217. Min Act: -0.1700

Data Index: 238273 (Open Web Text)

Max Activating Token Index: 735

Text #19

Max Range: 4.1306. Min Range: -4.1306

Max Act: 3.8752. Min Act: -0.1700

Data Index: 1498599 (Open Web Text)

Max Activating Token Index: 376