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

Dataset: Open Web Text

Neuron 1955 in Layer 2

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: 4.7811. Min Range: -4.7811

Max Act: 4.7811. Min Act: -0.1700

Data Index: 5861914 (Open Web Text)

Max Activating Token Index: 348

Text #1

Max Range: 4.7811. Min Range: -4.7811

Max Act: 4.7133. Min Act: -0.1700

Data Index: 1906257 (Open Web Text)

Max Activating Token Index: 467

Text #2

Max Range: 4.7811. Min Range: -4.7811

Max Act: 4.7226. Min Act: -0.1698

Data Index: 7298434 (Open Web Text)

Max Activating Token Index: 434

Text #3

Max Range: 4.7811. Min Range: -4.7811

Max Act: 4.7148. Min Act: -0.1699

Data Index: 102351 (Open Web Text)

Max Activating Token Index: 25

Text #4

Max Range: 4.7811. Min Range: -4.7811

Max Act: 4.7049. Min Act: -0.1700

Data Index: 2868677 (Open Web Text)

Max Activating Token Index: 311

Text #5

Max Range: 4.7811. Min Range: -4.7811

Max Act: 4.6882. Min Act: -0.1700

Data Index: 733587 (Open Web Text)

Max Activating Token Index: 271

Text #6

Max Range: 4.7811. Min Range: -4.7811

Max Act: 4.6905. Min Act: -0.1700

Data Index: 5272644 (Open Web Text)

Max Activating Token Index: 486

Text #7

Max Range: 4.7811. Min Range: -4.7811

Max Act: 4.6499. Min Act: -0.1700

Data Index: 7679072 (Open Web Text)

Max Activating Token Index: 451

Text #8

Max Range: 4.7811. Min Range: -4.7811

Max Act: 4.6842. Min Act: -0.1700

Data Index: 5063925 (Open Web Text)

Max Activating Token Index: 276

Text #9

Max Range: 4.7811. Min Range: -4.7811

Max Act: 4.6315. Min Act: -0.1700

Data Index: 3910521 (Open Web Text)

Max Activating Token Index: 438

Text #10

Max Range: 4.7811. Min Range: -4.7811

Max Act: 4.5873. Min Act: -0.1698

Data Index: 611794 (Open Web Text)

Max Activating Token Index: 520

Text #11

Max Range: 4.7811. Min Range: -4.7811

Max Act: 4.6285. Min Act: -0.1700

Data Index: 3307285 (Open Web Text)

Max Activating Token Index: 67

Text #12

Max Range: 4.7811. Min Range: -4.7811

Max Act: 4.5969. Min Act: -0.1700

Data Index: 4549322 (Open Web Text)

Max Activating Token Index: 1017

Text #13

Max Range: 4.7811. Min Range: -4.7811

Max Act: 4.6037. Min Act: -0.1699

Data Index: 7398535 (Open Web Text)

Max Activating Token Index: 385

Text #14

Max Range: 4.7811. Min Range: -4.7811

Max Act: 4.5802. Min Act: -0.1691

Data Index: 4216098 (Open Web Text)

Max Activating Token Index: 239

Text #15

Max Range: 4.7811. Min Range: -4.7811

Max Act: 4.6020. Min Act: -0.1683

Data Index: 4221292 (Open Web Text)

Max Activating Token Index: 567

Text #16

Max Range: 4.7811. Min Range: -4.7811

Max Act: 4.6087. Min Act: -0.1700

Data Index: 5267528 (Open Web Text)

Max Activating Token Index: 969

Text #17

Max Range: 4.7811. Min Range: -4.7811

Max Act: 4.6100. Min Act: -0.1698

Data Index: 5172044 (Open Web Text)

Max Activating Token Index: 98

Text #18

Max Range: 4.7811. Min Range: -4.7811

Max Act: 4.5886. Min Act: -0.1699

Data Index: 227125 (Open Web Text)

Max Activating Token Index: 641

Text #19

Max Range: 4.7811. Min Range: -4.7811

Max Act: 4.5937. Min Act: -0.1700

Data Index: 6891610 (Open Web Text)

Max Activating Token Index: 24