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

Dataset: Open Web Text

Neuron 1619 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: 2.8661. Min Range: -2.8661

Max Act: 2.8503. Min Act: -0.1700

Data Index: 3058575 (Open Web Text)

Max Activating Token Index: 14

Text #1

Max Range: 2.8661. Min Range: -2.8661

Max Act: 2.8636. Min Act: -0.1700

Data Index: 2750634 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 2.8661. Min Range: -2.8661

Max Act: 2.8661. Min Act: -0.1700

Data Index: 624082 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 2.8661. Min Range: -2.8661

Max Act: 2.8378. Min Act: -0.1700

Data Index: 4858074 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 2.8661. Min Range: -2.8661

Max Act: 2.8183. Min Act: -0.1700

Data Index: 8818339 (Open Web Text)

Max Activating Token Index: 25

Text #5

Max Range: 2.8661. Min Range: -2.8661

Max Act: 2.8146. Min Act: -0.1700

Data Index: 2182180 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 2.8661. Min Range: -2.8661

Max Act: 2.8207. Min Act: -0.1700

Data Index: 7760819 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 2.8661. Min Range: -2.8661

Max Act: 2.8315. Min Act: -0.1700

Data Index: 7153329 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.8661. Min Range: -2.8661

Max Act: 2.8284. Min Act: -0.1700

Data Index: 1168132 (Open Web Text)

Max Activating Token Index: 27

Text #9

Max Range: 2.8661. Min Range: -2.8661

Max Act: 2.8267. Min Act: -0.1700

Data Index: 4288587 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 2.8661. Min Range: -2.8661

Max Act: 2.8325. Min Act: -0.1700

Data Index: 1958803 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 2.8661. Min Range: -2.8661

Max Act: 2.8150. Min Act: -0.1700

Data Index: 4564084 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.8661. Min Range: -2.8661

Max Act: 2.8109. Min Act: -0.1700

Data Index: 2861395 (Open Web Text)

Max Activating Token Index: 13

Text #13

Max Range: 2.8661. Min Range: -2.8661

Max Act: 2.8008. Min Act: -0.1700

Data Index: 1275374 (Open Web Text)

Max Activating Token Index: 940

Text #14

Max Range: 2.8661. Min Range: -2.8661

Max Act: 2.8170. Min Act: -0.1700

Data Index: 2807610 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 2.8661. Min Range: -2.8661

Max Act: 2.8218. Min Act: -0.1700

Data Index: 7264503 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 2.8661. Min Range: -2.8661

Max Act: 2.8075. Min Act: -0.1700

Data Index: 1063477 (Open Web Text)

Max Activating Token Index: 47

Text #17

Max Range: 2.8661. Min Range: -2.8661

Max Act: 2.8121. Min Act: -0.1700

Data Index: 1055790 (Open Web Text)

Max Activating Token Index: 1021

Text #18

Max Range: 2.8661. Min Range: -2.8661

Max Act: 2.7944. Min Act: -0.1700

Data Index: 2115378 (Open Web Text)

Max Activating Token Index: 953

Text #19

Max Range: 2.8661. Min Range: -2.8661

Max Act: 2.8165. Min Act: -0.1700

Data Index: 6014201 (Open Web Text)

Max Activating Token Index: 6