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

Dataset: Open Web Text

Neuron 1965 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: 0.7898. Min Range: -0.7898

Max Act: 0.7898. Min Act: -0.1700

Data Index: 8530197 (Open Web Text)

Max Activating Token Index: 225

Text #1

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.7656. Min Act: -0.1700

Data Index: 8693806 (Open Web Text)

Max Activating Token Index: 192

Text #2

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.7599. Min Act: -0.1700

Data Index: 1705698 (Open Web Text)

Max Activating Token Index: 207

Text #3

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.7576. Min Act: -0.1700

Data Index: 6472606 (Open Web Text)

Max Activating Token Index: 200

Text #4

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.7532. Min Act: -0.1700

Data Index: 4690234 (Open Web Text)

Max Activating Token Index: 223

Text #5

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.7513. Min Act: -0.1700

Data Index: 4425801 (Open Web Text)

Max Activating Token Index: 197

Text #6

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.7505. Min Act: -0.1700

Data Index: 7706068 (Open Web Text)

Max Activating Token Index: 210

Text #7

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.7490. Min Act: -0.1700

Data Index: 7114333 (Open Web Text)

Max Activating Token Index: 210

Text #8

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.7476. Min Act: -0.1700

Data Index: 2272585 (Open Web Text)

Max Activating Token Index: 213

Text #9

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.7534. Min Act: -0.1700

Data Index: 5433049 (Open Web Text)

Max Activating Token Index: 206

Text #10

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.7441. Min Act: -0.1700

Data Index: 2967587 (Open Web Text)

Max Activating Token Index: 217

Text #11

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.7420. Min Act: -0.1700

Data Index: 6917170 (Open Web Text)

Max Activating Token Index: 191

Text #12

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.7472. Min Act: -0.1700

Data Index: 6881408 (Open Web Text)

Max Activating Token Index: 214

Text #13

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.7419. Min Act: -0.1700

Data Index: 2354201 (Open Web Text)

Max Activating Token Index: 198

Text #14

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.7470. Min Act: -0.1700

Data Index: 2523845 (Open Web Text)

Max Activating Token Index: 197

Text #15

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.7425. Min Act: -0.1700

Data Index: 2772240 (Open Web Text)

Max Activating Token Index: 226

Text #16

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.7443. Min Act: -0.1700

Data Index: 2613108 (Open Web Text)

Max Activating Token Index: 201

Text #17

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.7469. Min Act: -0.1700

Data Index: 767425 (Open Web Text)

Max Activating Token Index: 192

Text #18

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.7435. Min Act: -0.1700

Data Index: 2532336 (Open Web Text)

Max Activating Token Index: 225

Text #19

Max Range: 0.7898. Min Range: -0.7898

Max Act: 0.7350. Min Act: -0.1700

Data Index: 4473255 (Open Web Text)

Max Activating Token Index: 209