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

Dataset: Open Web Text

Neuron 305 in Layer 1

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: 4.4068. Min Range: -4.4068

Max Act: 4.4068. Min Act: -0.1700

Data Index: 3377635 (Open Web Text)

Max Activating Token Index: 668

Text #1

Max Range: 4.4068. Min Range: -4.4068

Max Act: 4.3652. Min Act: -0.1700

Data Index: 2880711 (Open Web Text)

Max Activating Token Index: 90

Text #2

Max Range: 4.4068. Min Range: -4.4068

Max Act: 4.3330. Min Act: -0.1700

Data Index: 1647784 (Open Web Text)

Max Activating Token Index: 15

Text #3

Max Range: 4.4068. Min Range: -4.4068

Max Act: 4.2946. Min Act: -0.1700

Data Index: 8610348 (Open Web Text)

Max Activating Token Index: 335

Text #4

Max Range: 4.4068. Min Range: -4.4068

Max Act: 4.3088. Min Act: -0.1700

Data Index: 4403038 (Open Web Text)

Max Activating Token Index: 98

Text #5

Max Range: 4.4068. Min Range: -4.4068

Max Act: 4.3009. Min Act: -0.1700

Data Index: 6913907 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.4068. Min Range: -4.4068

Max Act: 4.2916. Min Act: -0.1700

Data Index: 7562060 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.4068. Min Range: -4.4068

Max Act: 4.2753. Min Act: -0.1700

Data Index: 5787042 (Open Web Text)

Max Activating Token Index: 114

Text #8

Max Range: 4.4068. Min Range: -4.4068

Max Act: 4.2607. Min Act: -0.1700

Data Index: 474207 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 4.4068. Min Range: -4.4068

Max Act: 4.2749. Min Act: -0.1700

Data Index: 2514300 (Open Web Text)

Max Activating Token Index: 670

Text #10

Max Range: 4.4068. Min Range: -4.4068

Max Act: 4.2763. Min Act: -0.1700

Data Index: 6923350 (Open Web Text)

Max Activating Token Index: 36

Text #11

Max Range: 4.4068. Min Range: -4.4068

Max Act: 4.2578. Min Act: -0.1700

Data Index: 8562453 (Open Web Text)

Max Activating Token Index: 36

Text #12

Max Range: 4.4068. Min Range: -4.4068

Max Act: 4.2236. Min Act: -0.1700

Data Index: 2035681 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.4068. Min Range: -4.4068

Max Act: 4.2371. Min Act: -0.1700

Data Index: 3251682 (Open Web Text)

Max Activating Token Index: 40

Text #14

Max Range: 4.4068. Min Range: -4.4068

Max Act: 4.2319. Min Act: -0.1700

Data Index: 1560227 (Open Web Text)

Max Activating Token Index: 105

Text #15

Max Range: 4.4068. Min Range: -4.4068

Max Act: 4.2189. Min Act: -0.1700

Data Index: 2681918 (Open Web Text)

Max Activating Token Index: 80

Text #16

Max Range: 4.4068. Min Range: -4.4068

Max Act: 4.2252. Min Act: -0.1700

Data Index: 507656 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.4068. Min Range: -4.4068

Max Act: 4.2275. Min Act: -0.1700

Data Index: 879890 (Open Web Text)

Max Activating Token Index: 13

Text #18

Max Range: 4.4068. Min Range: -4.4068

Max Act: 4.2236. Min Act: -0.1700

Data Index: 2419566 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 4.4068. Min Range: -4.4068

Max Act: 4.2016. Min Act: -0.1700

Data Index: 1858612 (Open Web Text)

Max Activating Token Index: 7