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

Dataset: Open Web Text

Neuron 774 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: 4.1515. Min Range: -4.1515

Max Act: 4.1505. Min Act: -0.1700

Data Index: 79199 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 4.1515. Min Range: -4.1515

Max Act: 4.1515. Min Act: -0.1700

Data Index: 4322729 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 4.1515. Min Range: -4.1515

Max Act: 4.1352. Min Act: -0.1700

Data Index: 2828186 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 4.1515. Min Range: -4.1515

Max Act: 4.1150. Min Act: -0.1700

Data Index: 5273233 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.1515. Min Range: -4.1515

Max Act: 4.1334. Min Act: -0.1700

Data Index: 2173163 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.1515. Min Range: -4.1515

Max Act: 4.1163. Min Act: -0.1700

Data Index: 3724307 (Open Web Text)

Max Activating Token Index: 12

Text #6

Max Range: 4.1515. Min Range: -4.1515

Max Act: 4.1070. Min Act: -0.1700

Data Index: 8048551 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 4.1515. Min Range: -4.1515

Max Act: 4.0915. Min Act: -0.1700

Data Index: 2713733 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 4.1515. Min Range: -4.1515

Max Act: 4.1139. Min Act: -0.1700

Data Index: 8006906 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.1515. Min Range: -4.1515

Max Act: 4.1091. Min Act: -0.1700

Data Index: 7854120 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 4.1515. Min Range: -4.1515

Max Act: 4.0974. Min Act: -0.1700

Data Index: 4789960 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.1515. Min Range: -4.1515

Max Act: 4.1029. Min Act: -0.1700

Data Index: 7519768 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.1515. Min Range: -4.1515

Max Act: 4.1020. Min Act: -0.1700

Data Index: 1445509 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.1515. Min Range: -4.1515

Max Act: 4.0991. Min Act: -0.1700

Data Index: 4199550 (Open Web Text)

Max Activating Token Index: 13

Text #14

Max Range: 4.1515. Min Range: -4.1515

Max Act: 4.0941. Min Act: -0.1700

Data Index: 7132332 (Open Web Text)

Max Activating Token Index: 11

Text #15

Max Range: 4.1515. Min Range: -4.1515

Max Act: 4.0782. Min Act: -0.1700

Data Index: 3505769 (Open Web Text)

Max Activating Token Index: 947

Text #16

Max Range: 4.1515. Min Range: -4.1515

Max Act: 4.1095. Min Act: -0.1700

Data Index: 5847794 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 4.1515. Min Range: -4.1515

Max Act: 4.0963. Min Act: -0.1700

Data Index: 3181217 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.1515. Min Range: -4.1515

Max Act: 4.1010. Min Act: -0.1700

Data Index: 5625358 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.1515. Min Range: -4.1515

Max Act: 4.0856. Min Act: -0.1700

Data Index: 497002 (Open Web Text)

Max Activating Token Index: 10