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

Dataset: Open Web Text

Neuron 2733 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: 3.4252. Min Range: -3.4252

Max Act: 3.4252. Min Act: -0.1700

Data Index: 641346 (Open Web Text)

Max Activating Token Index: 400

Text #1

Max Range: 3.4252. Min Range: -3.4252

Max Act: 3.3500. Min Act: -0.1700

Data Index: 2852152 (Open Web Text)

Max Activating Token Index: 164

Text #2

Max Range: 3.4252. Min Range: -3.4252

Max Act: 3.2879. Min Act: -0.1700

Data Index: 8537679 (Open Web Text)

Max Activating Token Index: 52

Text #3

Max Range: 3.4252. Min Range: -3.4252

Max Act: 3.2714. Min Act: -0.1700

Data Index: 4208211 (Open Web Text)

Max Activating Token Index: 308

Text #4

Max Range: 3.4252. Min Range: -3.4252

Max Act: 3.2743. Min Act: -0.1700

Data Index: 5743554 (Open Web Text)

Max Activating Token Index: 251

Text #5

Max Range: 3.4252. Min Range: -3.4252

Max Act: 3.2312. Min Act: -0.1700

Data Index: 3882080 (Open Web Text)

Max Activating Token Index: 251

Text #6

Max Range: 3.4252. Min Range: -3.4252

Max Act: 3.2425. Min Act: -0.1700

Data Index: 6736321 (Open Web Text)

Max Activating Token Index: 358

Text #7

Max Range: 3.4252. Min Range: -3.4252

Max Act: 3.2078. Min Act: -0.1700

Data Index: 8479210 (Open Web Text)

Max Activating Token Index: 1008

Text #8

Max Range: 3.4252. Min Range: -3.4252

Max Act: 3.2156. Min Act: -0.1700

Data Index: 6613656 (Open Web Text)

Max Activating Token Index: 271

Text #9

Max Range: 3.4252. Min Range: -3.4252

Max Act: 3.2310. Min Act: -0.1700

Data Index: 2635918 (Open Web Text)

Max Activating Token Index: 827

Text #10

Max Range: 3.4252. Min Range: -3.4252

Max Act: 3.2207. Min Act: -0.1700

Data Index: 189747 (Open Web Text)

Max Activating Token Index: 369

Text #11

Max Range: 3.4252. Min Range: -3.4252

Max Act: 3.1839. Min Act: -0.1700

Data Index: 2247836 (Open Web Text)

Max Activating Token Index: 623

Text #12

Max Range: 3.4252. Min Range: -3.4252

Max Act: 3.1986. Min Act: -0.1700

Data Index: 8447237 (Open Web Text)

Max Activating Token Index: 982

Text #13

Max Range: 3.4252. Min Range: -3.4252

Max Act: 3.2142. Min Act: -0.1700

Data Index: 4353192 (Open Web Text)

Max Activating Token Index: 341

Text #14

Max Range: 3.4252. Min Range: -3.4252

Max Act: 3.2142. Min Act: -0.1700

Data Index: 1886510 (Open Web Text)

Max Activating Token Index: 588

Text #15

Max Range: 3.4252. Min Range: -3.4252

Max Act: 3.1840. Min Act: -0.1700

Data Index: 4623654 (Open Web Text)

Max Activating Token Index: 251

Text #16

Max Range: 3.4252. Min Range: -3.4252

Max Act: 3.2079. Min Act: -0.1700

Data Index: 2479148 (Open Web Text)

Max Activating Token Index: 399

Text #17

Max Range: 3.4252. Min Range: -3.4252

Max Act: 3.1889. Min Act: -0.1700

Data Index: 5666027 (Open Web Text)

Max Activating Token Index: 530

Text #18

Max Range: 3.4252. Min Range: -3.4252

Max Act: 3.1834. Min Act: -0.1700

Data Index: 5666031 (Open Web Text)

Max Activating Token Index: 442

Text #19

Max Range: 3.4252. Min Range: -3.4252

Max Act: 3.1749. Min Act: -0.1700

Data Index: 3471715 (Open Web Text)

Max Activating Token Index: 7