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

Dataset: Open Web Text

Neuron 1186 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: 5.6775. Min Range: -5.6775

Max Act: 5.6591. Min Act: -0.1700

Data Index: 2579687 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.6775. Min Range: -5.6775

Max Act: 5.6775. Min Act: -0.1700

Data Index: 7581151 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 5.6775. Min Range: -5.6775

Max Act: 5.6376. Min Act: -0.1700

Data Index: 4388718 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 5.6775. Min Range: -5.6775

Max Act: 5.6304. Min Act: -0.1700

Data Index: 2394169 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 5.6775. Min Range: -5.6775

Max Act: 5.5945. Min Act: -0.1700

Data Index: 4285610 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 5.6775. Min Range: -5.6775

Max Act: 5.6030. Min Act: -0.1700

Data Index: 8740417 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 5.6775. Min Range: -5.6775

Max Act: 5.6160. Min Act: -0.1700

Data Index: 7654364 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 5.6775. Min Range: -5.6775

Max Act: 5.5857. Min Act: -0.1700

Data Index: 50208 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 5.6775. Min Range: -5.6775

Max Act: 5.5710. Min Act: -0.1700

Data Index: 3642319 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 5.6775. Min Range: -5.6775

Max Act: 5.5750. Min Act: -0.1700

Data Index: 1236730 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 5.6775. Min Range: -5.6775

Max Act: 5.5593. Min Act: -0.1700

Data Index: 3130624 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 5.6775. Min Range: -5.6775

Max Act: 5.5828. Min Act: -0.1700

Data Index: 2887356 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 5.6775. Min Range: -5.6775

Max Act: 5.5543. Min Act: -0.1700

Data Index: 5827321 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 5.6775. Min Range: -5.6775

Max Act: 5.5461. Min Act: -0.1700

Data Index: 5055968 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 5.6775. Min Range: -5.6775

Max Act: 5.5241. Min Act: -0.1700

Data Index: 2633799 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 5.6775. Min Range: -5.6775

Max Act: 5.5432. Min Act: -0.1700

Data Index: 625796 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 5.6775. Min Range: -5.6775

Max Act: 5.5398. Min Act: -0.1700

Data Index: 933780 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 5.6775. Min Range: -5.6775

Max Act: 5.5372. Min Act: -0.1700

Data Index: 4788644 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 5.6775. Min Range: -5.6775

Max Act: 5.5564. Min Act: -0.1700

Data Index: 1621640 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 5.6775. Min Range: -5.6775

Max Act: 5.5138. Min Act: -0.1700

Data Index: 4325419 (Open Web Text)

Max Activating Token Index: 14