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

Dataset: Open Web Text

Neuron 703 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: 1.9104. Min Range: -1.9104

Max Act: 1.9104. Min Act: -0.1700

Data Index: 316119 (Open Web Text)

Max Activating Token Index: 667

Text #1

Max Range: 1.9104. Min Range: -1.9104

Max Act: 1.8930. Min Act: -0.1700

Data Index: 4327204 (Open Web Text)

Max Activating Token Index: 702

Text #2

Max Range: 1.9104. Min Range: -1.9104

Max Act: 1.8822. Min Act: -0.1699

Data Index: 2738918 (Open Web Text)

Max Activating Token Index: 615

Text #3

Max Range: 1.9104. Min Range: -1.9104

Max Act: 1.8851. Min Act: -0.1700

Data Index: 2683273 (Open Web Text)

Max Activating Token Index: 263

Text #4

Max Range: 1.9104. Min Range: -1.9104

Max Act: 1.8860. Min Act: -0.1699

Data Index: 3872707 (Open Web Text)

Max Activating Token Index: 218

Text #5

Max Range: 1.9104. Min Range: -1.9104

Max Act: 1.8856. Min Act: -0.1700

Data Index: 6006058 (Open Web Text)

Max Activating Token Index: 691

Text #6

Max Range: 1.9104. Min Range: -1.9104

Max Act: 1.8908. Min Act: -0.1700

Data Index: 5996295 (Open Web Text)

Max Activating Token Index: 269

Text #7

Max Range: 1.9104. Min Range: -1.9104

Max Act: 1.8847. Min Act: -0.1700

Data Index: 637329 (Open Web Text)

Max Activating Token Index: 261

Text #8

Max Range: 1.9104. Min Range: -1.9104

Max Act: 1.8870. Min Act: -0.1700

Data Index: 5151167 (Open Web Text)

Max Activating Token Index: 698

Text #9

Max Range: 1.9104. Min Range: -1.9104

Max Act: 1.8893. Min Act: -0.1700

Data Index: 6143577 (Open Web Text)

Max Activating Token Index: 230

Text #10

Max Range: 1.9104. Min Range: -1.9104

Max Act: 1.8780. Min Act: -0.1700

Data Index: 636510 (Open Web Text)

Max Activating Token Index: 416

Text #11

Max Range: 1.9104. Min Range: -1.9104

Max Act: 1.8811. Min Act: -0.1700

Data Index: 11919 (Open Web Text)

Max Activating Token Index: 189

Text #12

Max Range: 1.9104. Min Range: -1.9104

Max Act: 1.8780. Min Act: -0.1700

Data Index: 7390129 (Open Web Text)

Max Activating Token Index: 290

Text #13

Max Range: 1.9104. Min Range: -1.9104

Max Act: 1.8762. Min Act: -0.1700

Data Index: 8423114 (Open Web Text)

Max Activating Token Index: 798

Text #14

Max Range: 1.9104. Min Range: -1.9104

Max Act: 1.8689. Min Act: -0.1700

Data Index: 1141049 (Open Web Text)

Max Activating Token Index: 240

Text #15

Max Range: 1.9104. Min Range: -1.9104

Max Act: 1.8731. Min Act: -0.1700

Data Index: 835926 (Open Web Text)

Max Activating Token Index: 279

Text #16

Max Range: 1.9104. Min Range: -1.9104

Max Act: 1.8664. Min Act: -0.1700

Data Index: 6015817 (Open Web Text)

Max Activating Token Index: 347

Text #17

Max Range: 1.9104. Min Range: -1.9104

Max Act: 1.8556. Min Act: -0.1700

Data Index: 6990384 (Open Web Text)

Max Activating Token Index: 748

Text #18

Max Range: 1.9104. Min Range: -1.9104

Max Act: 1.8630. Min Act: -0.1700

Data Index: 6732371 (Open Web Text)

Max Activating Token Index: 229

Text #19

Max Range: 1.9104. Min Range: -1.9104

Max Act: 1.8660. Min Act: -0.1700

Data Index: 3880351 (Open Web Text)

Max Activating Token Index: 386