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

Dataset: Open Web Text

Neuron 1760 in Layer 4

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: 4.7808. Min Range: -4.7808

Max Act: 4.7808. Min Act: -0.1700

Data Index: 4555440 (Open Web Text)

Max Activating Token Index: 957

Text #1

Max Range: 4.7808. Min Range: -4.7808

Max Act: 4.7433. Min Act: -0.1700

Data Index: 3389231 (Open Web Text)

Max Activating Token Index: 483

Text #2

Max Range: 4.7808. Min Range: -4.7808

Max Act: 4.6601. Min Act: -0.1700

Data Index: 8149270 (Open Web Text)

Max Activating Token Index: 163

Text #3

Max Range: 4.7808. Min Range: -4.7808

Max Act: 4.6916. Min Act: -0.1700

Data Index: 2773143 (Open Web Text)

Max Activating Token Index: 714

Text #4

Max Range: 4.7808. Min Range: -4.7808

Max Act: 4.6449. Min Act: -0.1700

Data Index: 4889349 (Open Web Text)

Max Activating Token Index: 279

Text #5

Max Range: 4.7808. Min Range: -4.7808

Max Act: 4.6211. Min Act: -0.1700

Data Index: 5778989 (Open Web Text)

Max Activating Token Index: 828

Text #6

Max Range: 4.7808. Min Range: -4.7808

Max Act: 4.6314. Min Act: -0.1700

Data Index: 1302091 (Open Web Text)

Max Activating Token Index: 86

Text #7

Max Range: 4.7808. Min Range: -4.7808

Max Act: 4.6705. Min Act: -0.1700

Data Index: 799320 (Open Web Text)

Max Activating Token Index: 417

Text #8

Max Range: 4.7808. Min Range: -4.7808

Max Act: 4.5994. Min Act: -0.1700

Data Index: 4092625 (Open Web Text)

Max Activating Token Index: 331

Text #9

Max Range: 4.7808. Min Range: -4.7808

Max Act: 4.6331. Min Act: -0.1700

Data Index: 2712985 (Open Web Text)

Max Activating Token Index: 130

Text #10

Max Range: 4.7808. Min Range: -4.7808

Max Act: 4.6322. Min Act: -0.1700

Data Index: 6449606 (Open Web Text)

Max Activating Token Index: 395

Text #11

Max Range: 4.7808. Min Range: -4.7808

Max Act: 4.6273. Min Act: -0.1700

Data Index: 8415179 (Open Web Text)

Max Activating Token Index: 236

Text #12

Max Range: 4.7808. Min Range: -4.7808

Max Act: 4.6194. Min Act: -0.1700

Data Index: 3049284 (Open Web Text)

Max Activating Token Index: 720

Text #13

Max Range: 4.7808. Min Range: -4.7808

Max Act: 4.6318. Min Act: -0.1700

Data Index: 6695089 (Open Web Text)

Max Activating Token Index: 600

Text #14

Max Range: 4.7808. Min Range: -4.7808

Max Act: 4.6210. Min Act: -0.1700

Data Index: 5571692 (Open Web Text)

Max Activating Token Index: 238

Text #15

Max Range: 4.7808. Min Range: -4.7808

Max Act: 4.5921. Min Act: -0.1700

Data Index: 5899723 (Open Web Text)

Max Activating Token Index: 109

Text #16

Max Range: 4.7808. Min Range: -4.7808

Max Act: 4.5504. Min Act: -0.1700

Data Index: 5326321 (Open Web Text)

Max Activating Token Index: 781

Text #17

Max Range: 4.7808. Min Range: -4.7808

Max Act: 4.5314. Min Act: -0.1700

Data Index: 3874172 (Open Web Text)

Max Activating Token Index: 765

Text #18

Max Range: 4.7808. Min Range: -4.7808

Max Act: 4.5885. Min Act: -0.1700

Data Index: 6397739 (Open Web Text)

Max Activating Token Index: 928

Text #19

Max Range: 4.7808. Min Range: -4.7808

Max Act: 4.5878. Min Act: -0.1700

Data Index: 4387399 (Open Web Text)

Max Activating Token Index: 961