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

Dataset: Open Web Text

Neuron 2187 in Layer 1

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: 0.8707. Min Range: -0.8707

Max Act: 0.8707. Min Act: -0.1700

Data Index: 8536799 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.8428. Min Act: -0.1700

Data Index: 16884 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.8360. Min Act: -0.1700

Data Index: 5883551 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.8431. Min Act: -0.1700

Data Index: 4028677 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.8321. Min Act: -0.1700

Data Index: 1870855 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.8274. Min Act: -0.1700

Data Index: 5545159 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.8220. Min Act: -0.1700

Data Index: 3650040 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.8228. Min Act: -0.1700

Data Index: 2137673 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.8229. Min Act: -0.1700

Data Index: 3501640 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.8173. Min Act: -0.1700

Data Index: 8533624 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.8118. Min Act: -0.1700

Data Index: 2218124 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.8079. Min Act: -0.1700

Data Index: 7315179 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.8052. Min Act: -0.1700

Data Index: 2702136 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.8049. Min Act: -0.1700

Data Index: 2646445 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.8024. Min Act: -0.1700

Data Index: 4445225 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.8002. Min Act: -0.1700

Data Index: 4161739 (Open Web Text)

Max Activating Token Index: 1

Text #16

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.7953. Min Act: -0.1700

Data Index: 1890892 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.8002. Min Act: -0.1700

Data Index: 4153629 (Open Web Text)

Max Activating Token Index: 1

Text #18

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.8002. Min Act: -0.1700

Data Index: 2089421 (Open Web Text)

Max Activating Token Index: 1

Text #19

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.8002. Min Act: -0.1700

Data Index: 769621 (Open Web Text)

Max Activating Token Index: 1