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

Dataset: Open Web Text

Neuron 254 in Layer 5

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: 5.3630. Min Range: -5.3630

Max Act: 5.3630. Min Act: -0.1700

Data Index: 7146164 (Open Web Text)

Max Activating Token Index: 712

Text #1

Max Range: 5.3630. Min Range: -5.3630

Max Act: 5.3172. Min Act: -0.1700

Data Index: 8031845 (Open Web Text)

Max Activating Token Index: 526

Text #2

Max Range: 5.3630. Min Range: -5.3630

Max Act: 5.2980. Min Act: -0.1700

Data Index: 2599362 (Open Web Text)

Max Activating Token Index: 456

Text #3

Max Range: 5.3630. Min Range: -5.3630

Max Act: 5.2869. Min Act: -0.1700

Data Index: 2654177 (Open Web Text)

Max Activating Token Index: 580

Text #4

Max Range: 5.3630. Min Range: -5.3630

Max Act: 5.2640. Min Act: -0.1700

Data Index: 7984109 (Open Web Text)

Max Activating Token Index: 156

Text #5

Max Range: 5.3630. Min Range: -5.3630

Max Act: 5.2572. Min Act: -0.1700

Data Index: 5947570 (Open Web Text)

Max Activating Token Index: 866

Text #6

Max Range: 5.3630. Min Range: -5.3630

Max Act: 5.2512. Min Act: -0.1700

Data Index: 7707158 (Open Web Text)

Max Activating Token Index: 545

Text #7

Max Range: 5.3630. Min Range: -5.3630

Max Act: 5.2693. Min Act: -0.1700

Data Index: 8226922 (Open Web Text)

Max Activating Token Index: 511

Text #8

Max Range: 5.3630. Min Range: -5.3630

Max Act: 5.2881. Min Act: -0.1700

Data Index: 1530924 (Open Web Text)

Max Activating Token Index: 756

Text #9

Max Range: 5.3630. Min Range: -5.3630

Max Act: 5.2268. Min Act: -0.1700

Data Index: 1587892 (Open Web Text)

Max Activating Token Index: 205

Text #10

Max Range: 5.3630. Min Range: -5.3630

Max Act: 5.2143. Min Act: -0.1700

Data Index: 3386361 (Open Web Text)

Max Activating Token Index: 517

Text #11

Max Range: 5.3630. Min Range: -5.3630

Max Act: 5.2192. Min Act: -0.1700

Data Index: 6698636 (Open Web Text)

Max Activating Token Index: 906

Text #12

Max Range: 5.3630. Min Range: -5.3630

Max Act: 5.2449. Min Act: -0.1700

Data Index: 6573629 (Open Web Text)

Max Activating Token Index: 239

Text #13

Max Range: 5.3630. Min Range: -5.3630

Max Act: 5.2416. Min Act: -0.1700

Data Index: 1605572 (Open Web Text)

Max Activating Token Index: 535

Text #14

Max Range: 5.3630. Min Range: -5.3630

Max Act: 5.1702. Min Act: -0.1700

Data Index: 1674276 (Open Web Text)

Max Activating Token Index: 793

Text #15

Max Range: 5.3630. Min Range: -5.3630

Max Act: 5.1623. Min Act: -0.1700

Data Index: 2745031 (Open Web Text)

Max Activating Token Index: 681

Text #16

Max Range: 5.3630. Min Range: -5.3630

Max Act: 5.2155. Min Act: -0.1700

Data Index: 2660281 (Open Web Text)

Max Activating Token Index: 32

Text #17

Max Range: 5.3630. Min Range: -5.3630

Max Act: 5.2065. Min Act: -0.1700

Data Index: 1809641 (Open Web Text)

Max Activating Token Index: 870

Text #18

Max Range: 5.3630. Min Range: -5.3630

Max Act: 5.2322. Min Act: -0.1700

Data Index: 1469660 (Open Web Text)

Max Activating Token Index: 487

Text #19

Max Range: 5.3630. Min Range: -5.3630

Max Act: 5.1971. Min Act: -0.1700

Data Index: 423009 (Open Web Text)

Max Activating Token Index: 828