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

Dataset: Open Web Text

Neuron 214 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: 4.2249. Min Range: -4.2249

Max Act: 4.2249. Min Act: -0.1700

Data Index: 5252553 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 4.2249. Min Range: -4.2249

Max Act: 4.1886. Min Act: -0.1700

Data Index: 2395499 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 4.2249. Min Range: -4.2249

Max Act: 4.1788. Min Act: -0.1700

Data Index: 2889233 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.2249. Min Range: -4.2249

Max Act: 4.1547. Min Act: -0.1700

Data Index: 2372759 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 4.2249. Min Range: -4.2249

Max Act: 4.1558. Min Act: -0.1700

Data Index: 4692139 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 4.2249. Min Range: -4.2249

Max Act: 4.1564. Min Act: -0.1700

Data Index: 4697159 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.2249. Min Range: -4.2249

Max Act: 4.1259. Min Act: -0.1700

Data Index: 1553609 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 4.2249. Min Range: -4.2249

Max Act: 4.1372. Min Act: -0.1700

Data Index: 8054389 (Open Web Text)

Max Activating Token Index: 17

Text #8

Max Range: 4.2249. Min Range: -4.2249

Max Act: 4.1191. Min Act: -0.1700

Data Index: 5215688 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 4.2249. Min Range: -4.2249

Max Act: 4.0925. Min Act: -0.1700

Data Index: 7702448 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 4.2249. Min Range: -4.2249

Max Act: 4.1128. Min Act: -0.1700

Data Index: 7668254 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 4.2249. Min Range: -4.2249

Max Act: 4.0822. Min Act: -0.1700

Data Index: 4869078 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 4.2249. Min Range: -4.2249

Max Act: 4.0981. Min Act: -0.1700

Data Index: 4741603 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.2249. Min Range: -4.2249

Max Act: 4.0989. Min Act: -0.1700

Data Index: 7421228 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.2249. Min Range: -4.2249

Max Act: 4.0918. Min Act: -0.1700

Data Index: 7337770 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.2249. Min Range: -4.2249

Max Act: 4.0933. Min Act: -0.1700

Data Index: 6431236 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.2249. Min Range: -4.2249

Max Act: 4.0912. Min Act: -0.1700

Data Index: 1860850 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.2249. Min Range: -4.2249

Max Act: 4.1042. Min Act: -0.1700

Data Index: 5833435 (Open Web Text)

Max Activating Token Index: 11

Text #18

Max Range: 4.2249. Min Range: -4.2249

Max Act: 4.0961. Min Act: -0.1700

Data Index: 3906067 (Open Web Text)

Max Activating Token Index: 36

Text #19

Max Range: 4.2249. Min Range: -4.2249

Max Act: 4.0929. Min Act: -0.1700

Data Index: 1691716 (Open Web Text)

Max Activating Token Index: 5