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

Dataset: Open Web Text

Neuron 907 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: 1.0367. Min Range: -1.0367

Max Act: 1.0367. Min Act: -0.1700

Data Index: 6000087 (Open Web Text)

Max Activating Token Index: 921

Text #1

Max Range: 1.0367. Min Range: -1.0367

Max Act: 1.0311. Min Act: -0.1700

Data Index: 8155052 (Open Web Text)

Max Activating Token Index: 923

Text #2

Max Range: 1.0367. Min Range: -1.0367

Max Act: 1.0364. Min Act: -0.1700

Data Index: 4796638 (Open Web Text)

Max Activating Token Index: 923

Text #3

Max Range: 1.0367. Min Range: -1.0367

Max Act: 1.0330. Min Act: -0.1700

Data Index: 8510873 (Open Web Text)

Max Activating Token Index: 918

Text #4

Max Range: 1.0367. Min Range: -1.0367

Max Act: 1.0277. Min Act: -0.1700

Data Index: 2417316 (Open Web Text)

Max Activating Token Index: 930

Text #5

Max Range: 1.0367. Min Range: -1.0367

Max Act: 1.0156. Min Act: -0.1700

Data Index: 540096 (Open Web Text)

Max Activating Token Index: 929

Text #6

Max Range: 1.0367. Min Range: -1.0367

Max Act: 1.0096. Min Act: -0.1700

Data Index: 7946992 (Open Web Text)

Max Activating Token Index: 927

Text #7

Max Range: 1.0367. Min Range: -1.0367

Max Act: 1.0161. Min Act: -0.1700

Data Index: 3221401 (Open Web Text)

Max Activating Token Index: 930

Text #8

Max Range: 1.0367. Min Range: -1.0367

Max Act: 0.9997. Min Act: -0.1700

Data Index: 4426530 (Open Web Text)

Max Activating Token Index: 919

Text #9

Max Range: 1.0367. Min Range: -1.0367

Max Act: 1.0063. Min Act: -0.1700

Data Index: 1584264 (Open Web Text)

Max Activating Token Index: 931

Text #10

Max Range: 1.0367. Min Range: -1.0367

Max Act: 1.0047. Min Act: -0.1700

Data Index: 6520959 (Open Web Text)

Max Activating Token Index: 924

Text #11

Max Range: 1.0367. Min Range: -1.0367

Max Act: 1.0078. Min Act: -0.1700

Data Index: 4656563 (Open Web Text)

Max Activating Token Index: 938

Text #12

Max Range: 1.0367. Min Range: -1.0367

Max Act: 1.0053. Min Act: -0.1700

Data Index: 3475652 (Open Web Text)

Max Activating Token Index: 931

Text #13

Max Range: 1.0367. Min Range: -1.0367

Max Act: 1.0073. Min Act: -0.1700

Data Index: 4275168 (Open Web Text)

Max Activating Token Index: 923

Text #14

Max Range: 1.0367. Min Range: -1.0367

Max Act: 1.0119. Min Act: -0.1700

Data Index: 6912535 (Open Web Text)

Max Activating Token Index: 923

Text #15

Max Range: 1.0367. Min Range: -1.0367

Max Act: 1.0180. Min Act: -0.1700

Data Index: 4906150 (Open Web Text)

Max Activating Token Index: 918

Text #16

Max Range: 1.0367. Min Range: -1.0367

Max Act: 1.0000. Min Act: -0.1700

Data Index: 3252337 (Open Web Text)

Max Activating Token Index: 931

Text #17

Max Range: 1.0367. Min Range: -1.0367

Max Act: 1.0063. Min Act: -0.1700

Data Index: 406605 (Open Web Text)

Max Activating Token Index: 913

Text #18

Max Range: 1.0367. Min Range: -1.0367

Max Act: 0.9953. Min Act: -0.1700

Data Index: 6101221 (Open Web Text)

Max Activating Token Index: 919

Text #19

Max Range: 1.0367. Min Range: -1.0367

Max Act: 0.9995. Min Act: -0.1700

Data Index: 4905984 (Open Web Text)

Max Activating Token Index: 929