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

Dataset: Open Web Text

Neuron 2949 in Layer 6

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: 4.8188. Min Range: -4.8188

Max Act: 4.8188. Min Act: -0.1700

Data Index: 4181146 (Open Web Text)

Max Activating Token Index: 925

Text #1

Max Range: 4.8188. Min Range: -4.8188

Max Act: 4.6895. Min Act: -0.1700

Data Index: 6251605 (Open Web Text)

Max Activating Token Index: 951

Text #2

Max Range: 4.8188. Min Range: -4.8188

Max Act: 4.5484. Min Act: -0.1700

Data Index: 1414029 (Open Web Text)

Max Activating Token Index: 359

Text #3

Max Range: 4.8188. Min Range: -4.8188

Max Act: 4.5665. Min Act: -0.1700

Data Index: 536375 (Open Web Text)

Max Activating Token Index: 672

Text #4

Max Range: 4.8188. Min Range: -4.8188

Max Act: 4.4748. Min Act: -0.1700

Data Index: 5418285 (Open Web Text)

Max Activating Token Index: 748

Text #5

Max Range: 4.8188. Min Range: -4.8188

Max Act: 4.4462. Min Act: -0.1700

Data Index: 5670076 (Open Web Text)

Max Activating Token Index: 614

Text #6

Max Range: 4.8188. Min Range: -4.8188

Max Act: 4.4153. Min Act: -0.1700

Data Index: 1474299 (Open Web Text)

Max Activating Token Index: 174

Text #7

Max Range: 4.8188. Min Range: -4.8188

Max Act: 4.3921. Min Act: -0.1700

Data Index: 7262013 (Open Web Text)

Max Activating Token Index: 263

Text #8

Max Range: 4.8188. Min Range: -4.8188

Max Act: 4.4113. Min Act: -0.1700

Data Index: 2056513 (Open Web Text)

Max Activating Token Index: 500

Text #9

Max Range: 4.8188. Min Range: -4.8188

Max Act: 4.3960. Min Act: -0.1700

Data Index: 4987668 (Open Web Text)

Max Activating Token Index: 779

Text #10

Max Range: 4.8188. Min Range: -4.8188

Max Act: 4.3329. Min Act: -0.1700

Data Index: 7372303 (Open Web Text)

Max Activating Token Index: 907

Text #11

Max Range: 4.8188. Min Range: -4.8188

Max Act: 4.3137. Min Act: -0.1700

Data Index: 5721009 (Open Web Text)

Max Activating Token Index: 37

Text #12

Max Range: 4.8188. Min Range: -4.8188

Max Act: 4.3035. Min Act: -0.1700

Data Index: 5287508 (Open Web Text)

Max Activating Token Index: 303

Text #13

Max Range: 4.8188. Min Range: -4.8188

Max Act: 4.2421. Min Act: -0.1700

Data Index: 130407 (Open Web Text)

Max Activating Token Index: 908

Text #14

Max Range: 4.8188. Min Range: -4.8188

Max Act: 4.2565. Min Act: -0.1700

Data Index: 4911047 (Open Web Text)

Max Activating Token Index: 184

Text #15

Max Range: 4.8188. Min Range: -4.8188

Max Act: 4.2543. Min Act: -0.1700

Data Index: 6579649 (Open Web Text)

Max Activating Token Index: 455

Text #16

Max Range: 4.8188. Min Range: -4.8188

Max Act: 4.2384. Min Act: -0.1700

Data Index: 6580721 (Open Web Text)

Max Activating Token Index: 999

Text #17

Max Range: 4.8188. Min Range: -4.8188

Max Act: 4.2418. Min Act: -0.1700

Data Index: 1956710 (Open Web Text)

Max Activating Token Index: 783

Text #18

Max Range: 4.8188. Min Range: -4.8188

Max Act: 4.2951. Min Act: -0.1700

Data Index: 3673968 (Open Web Text)

Max Activating Token Index: 440

Text #19

Max Range: 4.8188. Min Range: -4.8188

Max Act: 4.2297. Min Act: -0.1700

Data Index: 6704280 (Open Web Text)

Max Activating Token Index: 636