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

Dataset: Open Web Text

Neuron 1414 in Layer 2

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: 1.8037. Min Range: -1.8037

Max Act: 1.8037. Min Act: -0.1700

Data Index: 7522213 (Open Web Text)

Max Activating Token Index: 170

Text #1

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.7721. Min Act: -0.1700

Data Index: 519445 (Open Web Text)

Max Activating Token Index: 471

Text #2

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.7433. Min Act: -0.1700

Data Index: 1756779 (Open Web Text)

Max Activating Token Index: 488

Text #3

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.7318. Min Act: -0.1700

Data Index: 3345977 (Open Web Text)

Max Activating Token Index: 122

Text #4

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.7351. Min Act: -0.1700

Data Index: 6164091 (Open Web Text)

Max Activating Token Index: 557

Text #5

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.7295. Min Act: -0.1700

Data Index: 3533056 (Open Web Text)

Max Activating Token Index: 471

Text #6

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.7208. Min Act: -0.1700

Data Index: 2603368 (Open Web Text)

Max Activating Token Index: 32

Text #7

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.7234. Min Act: -0.1700

Data Index: 2970219 (Open Web Text)

Max Activating Token Index: 867

Text #8

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.7093. Min Act: -0.1700

Data Index: 6193821 (Open Web Text)

Max Activating Token Index: 527

Text #9

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.7009. Min Act: -0.1700

Data Index: 2733411 (Open Web Text)

Max Activating Token Index: 329

Text #10

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.6888. Min Act: -0.1699

Data Index: 8392485 (Open Web Text)

Max Activating Token Index: 496

Text #11

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.7084. Min Act: -0.1699

Data Index: 4164162 (Open Web Text)

Max Activating Token Index: 283

Text #12

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.6985. Min Act: -0.1700

Data Index: 6901288 (Open Web Text)

Max Activating Token Index: 91

Text #13

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.6998. Min Act: -0.1700

Data Index: 1644354 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.6989. Min Act: -0.1694

Data Index: 523870 (Open Web Text)

Max Activating Token Index: 15

Text #15

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.6955. Min Act: -0.1699

Data Index: 5991805 (Open Web Text)

Max Activating Token Index: 347

Text #16

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.6968. Min Act: -0.1700

Data Index: 3420214 (Open Web Text)

Max Activating Token Index: 27

Text #17

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.6893. Min Act: -0.1700

Data Index: 5701193 (Open Web Text)

Max Activating Token Index: 521

Text #18

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.6936. Min Act: -0.1700

Data Index: 1064213 (Open Web Text)

Max Activating Token Index: 304

Text #19

Max Range: 1.8037. Min Range: -1.8037

Max Act: 1.6955. Min Act: -0.1700

Data Index: 3660803 (Open Web Text)

Max Activating Token Index: 485