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

Dataset: Open Web Text

Neuron 621 in Layer 0

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: 4.4315. Min Range: -4.4315

Max Act: 4.4315. Min Act: -0.1700

Data Index: 2321483 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.3291. Min Act: -0.1700

Data Index: 5664668 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.2784. Min Act: -0.1700

Data Index: 2633839 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.2945. Min Act: -0.1700

Data Index: 3994874 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.2485. Min Act: -0.1700

Data Index: 276458 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.2410. Min Act: -0.1700

Data Index: 8611449 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.1961. Min Act: -0.1700

Data Index: 3319085 (Open Web Text)

Max Activating Token Index: 998

Text #7

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.2064. Min Act: -0.1700

Data Index: 3612246 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.2271. Min Act: -0.1700

Data Index: 8316357 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.2107. Min Act: -0.1700

Data Index: 7092937 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.2049. Min Act: -0.1700

Data Index: 4210823 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.2290. Min Act: -0.1700

Data Index: 5682270 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.2119. Min Act: -0.1700

Data Index: 2619793 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.1892. Min Act: -0.1700

Data Index: 4819010 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.1756. Min Act: -0.1700

Data Index: 5461222 (Open Web Text)

Max Activating Token Index: 13

Text #15

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.2071. Min Act: -0.1700

Data Index: 3528587 (Open Web Text)

Max Activating Token Index: 1007

Text #16

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.1643. Min Act: -0.1700

Data Index: 5638932 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.2008. Min Act: -0.1700

Data Index: 2618406 (Open Web Text)

Max Activating Token Index: 399

Text #18

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.1814. Min Act: -0.1700

Data Index: 4134576 (Open Web Text)

Max Activating Token Index: 16

Text #19

Max Range: 4.4315. Min Range: -4.4315

Max Act: 4.1770. Min Act: -0.1700

Data Index: 1490606 (Open Web Text)

Max Activating Token Index: 13