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

Dataset: Open Web Text

Neuron 95 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: 4.2145. Min Range: -4.2145

Max Act: 4.2145. Min Act: -0.1700

Data Index: 6617113 (Open Web Text)

Max Activating Token Index: 313

Text #1

Max Range: 4.2145. Min Range: -4.2145

Max Act: 4.1895. Min Act: -0.1700

Data Index: 2745955 (Open Web Text)

Max Activating Token Index: 174

Text #2

Max Range: 4.2145. Min Range: -4.2145

Max Act: 4.1762. Min Act: -0.1700

Data Index: 6486233 (Open Web Text)

Max Activating Token Index: 875

Text #3

Max Range: 4.2145. Min Range: -4.2145

Max Act: 4.1544. Min Act: -0.1700

Data Index: 7612269 (Open Web Text)

Max Activating Token Index: 156

Text #4

Max Range: 4.2145. Min Range: -4.2145

Max Act: 4.1406. Min Act: -0.1700

Data Index: 5241681 (Open Web Text)

Max Activating Token Index: 26

Text #5

Max Range: 4.2145. Min Range: -4.2145

Max Act: 4.1377. Min Act: -0.1700

Data Index: 1150342 (Open Web Text)

Max Activating Token Index: 357

Text #6

Max Range: 4.2145. Min Range: -4.2145

Max Act: 4.1618. Min Act: -0.1700

Data Index: 8095315 (Open Web Text)

Max Activating Token Index: 256

Text #7

Max Range: 4.2145. Min Range: -4.2145

Max Act: 4.1573. Min Act: -0.1700

Data Index: 330525 (Open Web Text)

Max Activating Token Index: 105

Text #8

Max Range: 4.2145. Min Range: -4.2145

Max Act: 4.1288. Min Act: -0.1700

Data Index: 8068694 (Open Web Text)

Max Activating Token Index: 239

Text #9

Max Range: 4.2145. Min Range: -4.2145

Max Act: 4.1081. Min Act: -0.1700

Data Index: 131320 (Open Web Text)

Max Activating Token Index: 300

Text #10

Max Range: 4.2145. Min Range: -4.2145

Max Act: 4.1325. Min Act: -0.1700

Data Index: 3471668 (Open Web Text)

Max Activating Token Index: 134

Text #11

Max Range: 4.2145. Min Range: -4.2145

Max Act: 4.0866. Min Act: -0.1700

Data Index: 973179 (Open Web Text)

Max Activating Token Index: 217

Text #12

Max Range: 4.2145. Min Range: -4.2145

Max Act: 4.0920. Min Act: -0.1700

Data Index: 7179077 (Open Web Text)

Max Activating Token Index: 803

Text #13

Max Range: 4.2145. Min Range: -4.2145

Max Act: 4.0988. Min Act: -0.1700

Data Index: 1541891 (Open Web Text)

Max Activating Token Index: 385

Text #14

Max Range: 4.2145. Min Range: -4.2145

Max Act: 4.0882. Min Act: -0.1700

Data Index: 6435592 (Open Web Text)

Max Activating Token Index: 269

Text #15

Max Range: 4.2145. Min Range: -4.2145

Max Act: 4.1175. Min Act: -0.1700

Data Index: 2924102 (Open Web Text)

Max Activating Token Index: 789

Text #16

Max Range: 4.2145. Min Range: -4.2145

Max Act: 4.0948. Min Act: -0.1700

Data Index: 6168446 (Open Web Text)

Max Activating Token Index: 448

Text #17

Max Range: 4.2145. Min Range: -4.2145

Max Act: 4.0844. Min Act: -0.1700

Data Index: 210036 (Open Web Text)

Max Activating Token Index: 531

Text #18

Max Range: 4.2145. Min Range: -4.2145

Max Act: 4.0962. Min Act: -0.1700

Data Index: 4571539 (Open Web Text)

Max Activating Token Index: 767

Text #19

Max Range: 4.2145. Min Range: -4.2145

Max Act: 4.1038. Min Act: -0.1700

Data Index: 4207081 (Open Web Text)

Max Activating Token Index: 168