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

Dataset: Open Web Text

Neuron 1168 in Layer 4

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: 3.8159. Min Range: -3.8159

Max Act: 3.8159. Min Act: -0.1700

Data Index: 3253347 (Open Web Text)

Max Activating Token Index: 315

Text #1

Max Range: 3.8159. Min Range: -3.8159

Max Act: 3.5929. Min Act: -0.1700

Data Index: 6316 (Open Web Text)

Max Activating Token Index: 59

Text #2

Max Range: 3.8159. Min Range: -3.8159

Max Act: 3.5668. Min Act: -0.1700

Data Index: 3345736 (Open Web Text)

Max Activating Token Index: 75

Text #3

Max Range: 3.8159. Min Range: -3.8159

Max Act: 3.5580. Min Act: -0.1700

Data Index: 6585382 (Open Web Text)

Max Activating Token Index: 745

Text #4

Max Range: 3.8159. Min Range: -3.8159

Max Act: 3.5387. Min Act: -0.1700

Data Index: 2463047 (Open Web Text)

Max Activating Token Index: 281

Text #5

Max Range: 3.8159. Min Range: -3.8159

Max Act: 3.5262. Min Act: -0.1700

Data Index: 1704532 (Open Web Text)

Max Activating Token Index: 192

Text #6

Max Range: 3.8159. Min Range: -3.8159

Max Act: 3.5096. Min Act: -0.1700

Data Index: 6585380 (Open Web Text)

Max Activating Token Index: 348

Text #7

Max Range: 3.8159. Min Range: -3.8159

Max Act: 3.5065. Min Act: -0.1700

Data Index: 5632399 (Open Web Text)

Max Activating Token Index: 43

Text #8

Max Range: 3.8159. Min Range: -3.8159

Max Act: 3.4748. Min Act: -0.1700

Data Index: 95990 (Open Web Text)

Max Activating Token Index: 63

Text #9

Max Range: 3.8159. Min Range: -3.8159

Max Act: 3.4902. Min Act: -0.1700

Data Index: 2090534 (Open Web Text)

Max Activating Token Index: 76

Text #10

Max Range: 3.8159. Min Range: -3.8159

Max Act: 3.4578. Min Act: -0.1700

Data Index: 1555627 (Open Web Text)

Max Activating Token Index: 93

Text #11

Max Range: 3.8159. Min Range: -3.8159

Max Act: 3.4766. Min Act: -0.1700

Data Index: 268393 (Open Web Text)

Max Activating Token Index: 729

Text #12

Max Range: 3.8159. Min Range: -3.8159

Max Act: 3.4280. Min Act: -0.1700

Data Index: 2159752 (Open Web Text)

Max Activating Token Index: 149

Text #13

Max Range: 3.8159. Min Range: -3.8159

Max Act: 3.4451. Min Act: -0.1700

Data Index: 1116014 (Open Web Text)

Max Activating Token Index: 193

Text #14

Max Range: 3.8159. Min Range: -3.8159

Max Act: 3.4365. Min Act: -0.1700

Data Index: 1825980 (Open Web Text)

Max Activating Token Index: 300

Text #15

Max Range: 3.8159. Min Range: -3.8159

Max Act: 3.4222. Min Act: -0.1700

Data Index: 4080805 (Open Web Text)

Max Activating Token Index: 638

Text #16

Max Range: 3.8159. Min Range: -3.8159

Max Act: 3.4312. Min Act: -0.1700

Data Index: 5171280 (Open Web Text)

Max Activating Token Index: 145

Text #17

Max Range: 3.8159. Min Range: -3.8159

Max Act: 3.4392. Min Act: -0.1700

Data Index: 992430 (Open Web Text)

Max Activating Token Index: 464

Text #18

Max Range: 3.8159. Min Range: -3.8159

Max Act: 3.4106. Min Act: -0.1700

Data Index: 2211376 (Open Web Text)

Max Activating Token Index: 13

Text #19

Max Range: 3.8159. Min Range: -3.8159

Max Act: 3.4146. Min Act: -0.1700

Data Index: 3022226 (Open Web Text)

Max Activating Token Index: 35