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

Dataset: Open Web Text

Neuron 938 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: 4.4064. Min Range: -4.4064

Max Act: 4.4064. Min Act: -0.1700

Data Index: 4342586 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.3076. Min Act: -0.1700

Data Index: 3613874 (Open Web Text)

Max Activating Token Index: 18

Text #2

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.2812. Min Act: -0.1700

Data Index: 8126035 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.2797. Min Act: -0.1700

Data Index: 8020090 (Open Web Text)

Max Activating Token Index: 17

Text #4

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.2865. Min Act: -0.1700

Data Index: 1228438 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.2641. Min Act: -0.1700

Data Index: 5986229 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.2346. Min Act: -0.1700

Data Index: 7908930 (Open Web Text)

Max Activating Token Index: 22

Text #7

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.2403. Min Act: -0.1700

Data Index: 7341705 (Open Web Text)

Max Activating Token Index: 29

Text #8

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.2305. Min Act: -0.1700

Data Index: 5215049 (Open Web Text)

Max Activating Token Index: 13

Text #9

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.2509. Min Act: -0.1700

Data Index: 1006860 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.2316. Min Act: -0.1700

Data Index: 4964867 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.2517. Min Act: -0.1700

Data Index: 4113830 (Open Web Text)

Max Activating Token Index: 14

Text #12

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.2087. Min Act: -0.1700

Data Index: 2646264 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.2182. Min Act: -0.1700

Data Index: 2788461 (Open Web Text)

Max Activating Token Index: 105

Text #14

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.2070. Min Act: -0.1700

Data Index: 878364 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.2147. Min Act: -0.1700

Data Index: 5722847 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.2108. Min Act: -0.1700

Data Index: 8011625 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.2253. Min Act: -0.1700

Data Index: 1150416 (Open Web Text)

Max Activating Token Index: 31

Text #18

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.2280. Min Act: -0.1700

Data Index: 46339 (Open Web Text)

Max Activating Token Index: 13

Text #19

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.2212. Min Act: -0.1700

Data Index: 1855231 (Open Web Text)

Max Activating Token Index: 4