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

Dataset: Open Web Text

Neuron 1480 in Layer 2

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: 4.3614. Min Range: -4.3614

Max Act: 4.3614. Min Act: -0.1700

Data Index: 735432 (Open Web Text)

Max Activating Token Index: 614

Text #1

Max Range: 4.3614. Min Range: -4.3614

Max Act: 4.2815. Min Act: -0.1700

Data Index: 4031020 (Open Web Text)

Max Activating Token Index: 366

Text #2

Max Range: 4.3614. Min Range: -4.3614

Max Act: 4.3113. Min Act: -0.1700

Data Index: 2392512 (Open Web Text)

Max Activating Token Index: 330

Text #3

Max Range: 4.3614. Min Range: -4.3614

Max Act: 4.2803. Min Act: -0.1700

Data Index: 601118 (Open Web Text)

Max Activating Token Index: 287

Text #4

Max Range: 4.3614. Min Range: -4.3614

Max Act: 4.2310. Min Act: -0.1700

Data Index: 77881 (Open Web Text)

Max Activating Token Index: 482

Text #5

Max Range: 4.3614. Min Range: -4.3614

Max Act: 4.2274. Min Act: -0.1700

Data Index: 6374586 (Open Web Text)

Max Activating Token Index: 854

Text #6

Max Range: 4.3614. Min Range: -4.3614

Max Act: 4.2480. Min Act: -0.1700

Data Index: 272850 (Open Web Text)

Max Activating Token Index: 263

Text #7

Max Range: 4.3614. Min Range: -4.3614

Max Act: 4.2542. Min Act: -0.1700

Data Index: 4758576 (Open Web Text)

Max Activating Token Index: 872

Text #8

Max Range: 4.3614. Min Range: -4.3614

Max Act: 4.2386. Min Act: -0.1700

Data Index: 1705246 (Open Web Text)

Max Activating Token Index: 963

Text #9

Max Range: 4.3614. Min Range: -4.3614

Max Act: 4.2252. Min Act: -0.1700

Data Index: 8020359 (Open Web Text)

Max Activating Token Index: 446

Text #10

Max Range: 4.3614. Min Range: -4.3614

Max Act: 4.1994. Min Act: -0.1700

Data Index: 1744874 (Open Web Text)

Max Activating Token Index: 475

Text #11

Max Range: 4.3614. Min Range: -4.3614

Max Act: 4.1921. Min Act: -0.1700

Data Index: 3627050 (Open Web Text)

Max Activating Token Index: 541

Text #12

Max Range: 4.3614. Min Range: -4.3614

Max Act: 4.2215. Min Act: -0.1700

Data Index: 166051 (Open Web Text)

Max Activating Token Index: 312

Text #13

Max Range: 4.3614. Min Range: -4.3614

Max Act: 4.2097. Min Act: -0.1700

Data Index: 2772687 (Open Web Text)

Max Activating Token Index: 363

Text #14

Max Range: 4.3614. Min Range: -4.3614

Max Act: 4.2095. Min Act: -0.1700

Data Index: 4871516 (Open Web Text)

Max Activating Token Index: 237

Text #15

Max Range: 4.3614. Min Range: -4.3614

Max Act: 4.1899. Min Act: -0.1700

Data Index: 5122269 (Open Web Text)

Max Activating Token Index: 663

Text #16

Max Range: 4.3614. Min Range: -4.3614

Max Act: 4.1981. Min Act: -0.1700

Data Index: 5393186 (Open Web Text)

Max Activating Token Index: 185

Text #17

Max Range: 4.3614. Min Range: -4.3614

Max Act: 4.1904. Min Act: -0.1700

Data Index: 6137109 (Open Web Text)

Max Activating Token Index: 107

Text #18

Max Range: 4.3614. Min Range: -4.3614

Max Act: 4.2280. Min Act: -0.1700

Data Index: 905103 (Open Web Text)

Max Activating Token Index: 542

Text #19

Max Range: 4.3614. Min Range: -4.3614

Max Act: 4.2050. Min Act: -0.1700

Data Index: 818121 (Open Web Text)

Max Activating Token Index: 275