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

Dataset: Open Web Text

Neuron 1902 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: 3.0863. Min Range: -3.0863

Max Act: 3.0863. Min Act: -0.1700

Data Index: 3882301 (Open Web Text)

Max Activating Token Index: 844

Text #1

Max Range: 3.0863. Min Range: -3.0863

Max Act: 3.0101. Min Act: -0.1700

Data Index: 7787963 (Open Web Text)

Max Activating Token Index: 744

Text #2

Max Range: 3.0863. Min Range: -3.0863

Max Act: 3.0364. Min Act: -0.1700

Data Index: 6187947 (Open Web Text)

Max Activating Token Index: 228

Text #3

Max Range: 3.0863. Min Range: -3.0863

Max Act: 2.9303. Min Act: -0.1700

Data Index: 7641886 (Open Web Text)

Max Activating Token Index: 353

Text #4

Max Range: 3.0863. Min Range: -3.0863

Max Act: 2.8973. Min Act: -0.1700

Data Index: 24287 (Open Web Text)

Max Activating Token Index: 275

Text #5

Max Range: 3.0863. Min Range: -3.0863

Max Act: 2.8911. Min Act: -0.1700

Data Index: 4164062 (Open Web Text)

Max Activating Token Index: 553

Text #6

Max Range: 3.0863. Min Range: -3.0863

Max Act: 2.9192. Min Act: -0.1700

Data Index: 2351143 (Open Web Text)

Max Activating Token Index: 76

Text #7

Max Range: 3.0863. Min Range: -3.0863

Max Act: 2.9028. Min Act: -0.1700

Data Index: 8138303 (Open Web Text)

Max Activating Token Index: 251

Text #8

Max Range: 3.0863. Min Range: -3.0863

Max Act: 2.8796. Min Act: -0.1700

Data Index: 8675962 (Open Web Text)

Max Activating Token Index: 224

Text #9

Max Range: 3.0863. Min Range: -3.0863

Max Act: 2.8459. Min Act: -0.1700

Data Index: 449647 (Open Web Text)

Max Activating Token Index: 312

Text #10

Max Range: 3.0863. Min Range: -3.0863

Max Act: 2.8303. Min Act: -0.1700

Data Index: 1746289 (Open Web Text)

Max Activating Token Index: 421

Text #11

Max Range: 3.0863. Min Range: -3.0863

Max Act: 2.8574. Min Act: -0.1700

Data Index: 8251746 (Open Web Text)

Max Activating Token Index: 307

Text #12

Max Range: 3.0863. Min Range: -3.0863

Max Act: 2.8414. Min Act: -0.1700

Data Index: 4381699 (Open Web Text)

Max Activating Token Index: 493

Text #13

Max Range: 3.0863. Min Range: -3.0863

Max Act: 2.8411. Min Act: -0.1700

Data Index: 1652339 (Open Web Text)

Max Activating Token Index: 673

Text #14

Max Range: 3.0863. Min Range: -3.0863

Max Act: 2.8174. Min Act: -0.1700

Data Index: 3709128 (Open Web Text)

Max Activating Token Index: 527

Text #15

Max Range: 3.0863. Min Range: -3.0863

Max Act: 2.7724. Min Act: -0.1700

Data Index: 360225 (Open Web Text)

Max Activating Token Index: 199

Text #16

Max Range: 3.0863. Min Range: -3.0863

Max Act: 2.7989. Min Act: -0.1700

Data Index: 7128920 (Open Web Text)

Max Activating Token Index: 242

Text #17

Max Range: 3.0863. Min Range: -3.0863

Max Act: 2.8040. Min Act: -0.1700

Data Index: 3839242 (Open Web Text)

Max Activating Token Index: 154

Text #18

Max Range: 3.0863. Min Range: -3.0863

Max Act: 2.8161. Min Act: -0.1700

Data Index: 2871367 (Open Web Text)

Max Activating Token Index: 319

Text #19

Max Range: 3.0863. Min Range: -3.0863

Max Act: 2.7790. Min Act: -0.1700

Data Index: 962148 (Open Web Text)

Max Activating Token Index: 23