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

Dataset: Open Web Text

Neuron 2158 in Layer 3

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: 4.5058. Min Range: -4.5058

Max Act: 4.5058. Min Act: -0.1700

Data Index: 1774361 (Open Web Text)

Max Activating Token Index: 894

Text #1

Max Range: 4.5058. Min Range: -4.5058

Max Act: 4.4552. Min Act: -0.1700

Data Index: 2881185 (Open Web Text)

Max Activating Token Index: 404

Text #2

Max Range: 4.5058. Min Range: -4.5058

Max Act: 4.4445. Min Act: -0.1700

Data Index: 8048165 (Open Web Text)

Max Activating Token Index: 26

Text #3

Max Range: 4.5058. Min Range: -4.5058

Max Act: 4.4129. Min Act: -0.1700

Data Index: 7761568 (Open Web Text)

Max Activating Token Index: 457

Text #4

Max Range: 4.5058. Min Range: -4.5058

Max Act: 4.3246. Min Act: -0.1700

Data Index: 6643258 (Open Web Text)

Max Activating Token Index: 455

Text #5

Max Range: 4.5058. Min Range: -4.5058

Max Act: 4.3362. Min Act: -0.1700

Data Index: 487013 (Open Web Text)

Max Activating Token Index: 138

Text #6

Max Range: 4.5058. Min Range: -4.5058

Max Act: 4.2957. Min Act: -0.1700

Data Index: 3145377 (Open Web Text)

Max Activating Token Index: 946

Text #7

Max Range: 4.5058. Min Range: -4.5058

Max Act: 4.2918. Min Act: -0.1700

Data Index: 1697976 (Open Web Text)

Max Activating Token Index: 529

Text #8

Max Range: 4.5058. Min Range: -4.5058

Max Act: 4.3489. Min Act: -0.1700

Data Index: 7185450 (Open Web Text)

Max Activating Token Index: 685

Text #9

Max Range: 4.5058. Min Range: -4.5058

Max Act: 4.3816. Min Act: -0.1700

Data Index: 953610 (Open Web Text)

Max Activating Token Index: 487

Text #10

Max Range: 4.5058. Min Range: -4.5058

Max Act: 4.3703. Min Act: -0.1700

Data Index: 3595294 (Open Web Text)

Max Activating Token Index: 1022

Text #11

Max Range: 4.5058. Min Range: -4.5058

Max Act: 4.2949. Min Act: -0.1700

Data Index: 4431557 (Open Web Text)

Max Activating Token Index: 84

Text #12

Max Range: 4.5058. Min Range: -4.5058

Max Act: 4.3031. Min Act: -0.1700

Data Index: 91812 (Open Web Text)

Max Activating Token Index: 682

Text #13

Max Range: 4.5058. Min Range: -4.5058

Max Act: 4.2904. Min Act: -0.1700

Data Index: 7225511 (Open Web Text)

Max Activating Token Index: 655

Text #14

Max Range: 4.5058. Min Range: -4.5058

Max Act: 4.2993. Min Act: -0.1700

Data Index: 3779548 (Open Web Text)

Max Activating Token Index: 225

Text #15

Max Range: 4.5058. Min Range: -4.5058

Max Act: 4.2838. Min Act: -0.1700

Data Index: 677914 (Open Web Text)

Max Activating Token Index: 41

Text #16

Max Range: 4.5058. Min Range: -4.5058

Max Act: 4.3003. Min Act: -0.1700

Data Index: 5244809 (Open Web Text)

Max Activating Token Index: 707

Text #17

Max Range: 4.5058. Min Range: -4.5058

Max Act: 4.2585. Min Act: -0.1700

Data Index: 157015 (Open Web Text)

Max Activating Token Index: 488

Text #18

Max Range: 4.5058. Min Range: -4.5058

Max Act: 4.2446. Min Act: -0.1700

Data Index: 3323923 (Open Web Text)

Max Activating Token Index: 702

Text #19

Max Range: 4.5058. Min Range: -4.5058

Max Act: 4.2490. Min Act: -0.1700

Data Index: 6609983 (Open Web Text)

Max Activating Token Index: 393