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

Dataset: Open Web Text

Neuron 1854 in Layer 4

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: 3.3235. Min Range: -3.3235

Max Act: 3.3235. Min Act: -0.1700

Data Index: 532715 (Open Web Text)

Max Activating Token Index: 929

Text #1

Max Range: 3.3235. Min Range: -3.3235

Max Act: 3.3214. Min Act: -0.1700

Data Index: 2307428 (Open Web Text)

Max Activating Token Index: 297

Text #2

Max Range: 3.3235. Min Range: -3.3235

Max Act: 3.2746. Min Act: -0.1700

Data Index: 8202101 (Open Web Text)

Max Activating Token Index: 738

Text #3

Max Range: 3.3235. Min Range: -3.3235

Max Act: 3.2745. Min Act: -0.1700

Data Index: 1408786 (Open Web Text)

Max Activating Token Index: 860

Text #4

Max Range: 3.3235. Min Range: -3.3235

Max Act: 3.2650. Min Act: -0.1700

Data Index: 1075244 (Open Web Text)

Max Activating Token Index: 817

Text #5

Max Range: 3.3235. Min Range: -3.3235

Max Act: 3.2563. Min Act: -0.1700

Data Index: 2982846 (Open Web Text)

Max Activating Token Index: 43

Text #6

Max Range: 3.3235. Min Range: -3.3235

Max Act: 3.2467. Min Act: -0.1700

Data Index: 425731 (Open Web Text)

Max Activating Token Index: 530

Text #7

Max Range: 3.3235. Min Range: -3.3235

Max Act: 3.2685. Min Act: -0.1700

Data Index: 1636047 (Open Web Text)

Max Activating Token Index: 204

Text #8

Max Range: 3.3235. Min Range: -3.3235

Max Act: 3.2485. Min Act: -0.1700

Data Index: 159000 (Open Web Text)

Max Activating Token Index: 190

Text #9

Max Range: 3.3235. Min Range: -3.3235

Max Act: 3.2481. Min Act: -0.1700

Data Index: 2376026 (Open Web Text)

Max Activating Token Index: 798

Text #10

Max Range: 3.3235. Min Range: -3.3235

Max Act: 3.2402. Min Act: -0.1700

Data Index: 3881716 (Open Web Text)

Max Activating Token Index: 478

Text #11

Max Range: 3.3235. Min Range: -3.3235

Max Act: 3.2270. Min Act: -0.1700

Data Index: 6669832 (Open Web Text)

Max Activating Token Index: 244

Text #12

Max Range: 3.3235. Min Range: -3.3235

Max Act: 3.2222. Min Act: -0.1700

Data Index: 2472457 (Open Web Text)

Max Activating Token Index: 501

Text #13

Max Range: 3.3235. Min Range: -3.3235

Max Act: 3.2230. Min Act: -0.1700

Data Index: 3388208 (Open Web Text)

Max Activating Token Index: 532

Text #14

Max Range: 3.3235. Min Range: -3.3235

Max Act: 3.2171. Min Act: -0.1700

Data Index: 2096698 (Open Web Text)

Max Activating Token Index: 541

Text #15

Max Range: 3.3235. Min Range: -3.3235

Max Act: 3.2222. Min Act: -0.1700

Data Index: 1915134 (Open Web Text)

Max Activating Token Index: 235

Text #16

Max Range: 3.3235. Min Range: -3.3235

Max Act: 3.2311. Min Act: -0.1700

Data Index: 8220168 (Open Web Text)

Max Activating Token Index: 497

Text #17

Max Range: 3.3235. Min Range: -3.3235

Max Act: 3.2246. Min Act: -0.1700

Data Index: 7592523 (Open Web Text)

Max Activating Token Index: 233

Text #18

Max Range: 3.3235. Min Range: -3.3235

Max Act: 3.1937. Min Act: -0.1700

Data Index: 3813697 (Open Web Text)

Max Activating Token Index: 1005

Text #19

Max Range: 3.3235. Min Range: -3.3235

Max Act: 3.2063. Min Act: -0.1700

Data Index: 3026832 (Open Web Text)

Max Activating Token Index: 745