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

Dataset: Open Web Text

Neuron 2520 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: 8.4078. Min Range: -8.4078

Max Act: 8.4078. Min Act: -0.1700

Data Index: 1151345 (Open Web Text)

Max Activating Token Index: 968

Text #1

Max Range: 8.4078. Min Range: -8.4078

Max Act: 8.3278. Min Act: -0.1700

Data Index: 8321150 (Open Web Text)

Max Activating Token Index: 232

Text #2

Max Range: 8.4078. Min Range: -8.4078

Max Act: 8.2396. Min Act: -0.1700

Data Index: 2696455 (Open Web Text)

Max Activating Token Index: 934

Text #3

Max Range: 8.4078. Min Range: -8.4078

Max Act: 8.2194. Min Act: -0.1700

Data Index: 6989676 (Open Web Text)

Max Activating Token Index: 273

Text #4

Max Range: 8.4078. Min Range: -8.4078

Max Act: 8.2169. Min Act: -0.1700

Data Index: 4506428 (Open Web Text)

Max Activating Token Index: 56

Text #5

Max Range: 8.4078. Min Range: -8.4078

Max Act: 8.2576. Min Act: -0.1700

Data Index: 3950734 (Open Web Text)

Max Activating Token Index: 856

Text #6

Max Range: 8.4078. Min Range: -8.4078

Max Act: 8.2709. Min Act: -0.1700

Data Index: 1550771 (Open Web Text)

Max Activating Token Index: 387

Text #7

Max Range: 8.4078. Min Range: -8.4078

Max Act: 8.1346. Min Act: -0.1700

Data Index: 7931195 (Open Web Text)

Max Activating Token Index: 947

Text #8

Max Range: 8.4078. Min Range: -8.4078

Max Act: 8.1797. Min Act: -0.1700

Data Index: 1008217 (Open Web Text)

Max Activating Token Index: 461

Text #9

Max Range: 8.4078. Min Range: -8.4078

Max Act: 8.2016. Min Act: -0.1700

Data Index: 8369426 (Open Web Text)

Max Activating Token Index: 901

Text #10

Max Range: 8.4078. Min Range: -8.4078

Max Act: 8.1797. Min Act: -0.1700

Data Index: 104652 (Open Web Text)

Max Activating Token Index: 534

Text #11

Max Range: 8.4078. Min Range: -8.4078

Max Act: 8.1704. Min Act: -0.1700

Data Index: 7837439 (Open Web Text)

Max Activating Token Index: 895

Text #12

Max Range: 8.4078. Min Range: -8.4078

Max Act: 8.1311. Min Act: -0.1700

Data Index: 6927131 (Open Web Text)

Max Activating Token Index: 772

Text #13

Max Range: 8.4078. Min Range: -8.4078

Max Act: 8.0596. Min Act: -0.1700

Data Index: 1772667 (Open Web Text)

Max Activating Token Index: 930

Text #14

Max Range: 8.4078. Min Range: -8.4078

Max Act: 8.0073. Min Act: -0.1700

Data Index: 5833169 (Open Web Text)

Max Activating Token Index: 492

Text #15

Max Range: 8.4078. Min Range: -8.4078

Max Act: 8.0037. Min Act: -0.1700

Data Index: 409269 (Open Web Text)

Max Activating Token Index: 740

Text #16

Max Range: 8.4078. Min Range: -8.4078

Max Act: 8.0194. Min Act: -0.1700

Data Index: 2892056 (Open Web Text)

Max Activating Token Index: 76

Text #17

Max Range: 8.4078. Min Range: -8.4078

Max Act: 8.0054. Min Act: -0.1700

Data Index: 2260185 (Open Web Text)

Max Activating Token Index: 373

Text #18

Max Range: 8.4078. Min Range: -8.4078

Max Act: 8.0347. Min Act: -0.1700

Data Index: 6741494 (Open Web Text)

Max Activating Token Index: 757

Text #19

Max Range: 8.4078. Min Range: -8.4078

Max Act: 8.0491. Min Act: -0.1700

Data Index: 8727789 (Open Web Text)

Max Activating Token Index: 838