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

Dataset: Open Web Text

Neuron 2469 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: 3.5485. Min Range: -3.5485

Max Act: 3.5485. Min Act: -0.1700

Data Index: 4683409 (Open Web Text)

Max Activating Token Index: 608

Text #1

Max Range: 3.5485. Min Range: -3.5485

Max Act: 3.4821. Min Act: -0.1700

Data Index: 2091033 (Open Web Text)

Max Activating Token Index: 66

Text #2

Max Range: 3.5485. Min Range: -3.5485

Max Act: 3.4443. Min Act: -0.1700

Data Index: 979868 (Open Web Text)

Max Activating Token Index: 359

Text #3

Max Range: 3.5485. Min Range: -3.5485

Max Act: 3.4275. Min Act: -0.1700

Data Index: 3611429 (Open Web Text)

Max Activating Token Index: 616

Text #4

Max Range: 3.5485. Min Range: -3.5485

Max Act: 3.4216. Min Act: -0.1700

Data Index: 8148397 (Open Web Text)

Max Activating Token Index: 90

Text #5

Max Range: 3.5485. Min Range: -3.5485

Max Act: 3.4817. Min Act: -0.1700

Data Index: 5365567 (Open Web Text)

Max Activating Token Index: 432

Text #6

Max Range: 3.5485. Min Range: -3.5485

Max Act: 3.4087. Min Act: -0.1700

Data Index: 260463 (Open Web Text)

Max Activating Token Index: 390

Text #7

Max Range: 3.5485. Min Range: -3.5485

Max Act: 3.3947. Min Act: -0.1700

Data Index: 666392 (Open Web Text)

Max Activating Token Index: 738

Text #8

Max Range: 3.5485. Min Range: -3.5485

Max Act: 3.3823. Min Act: -0.1700

Data Index: 1769084 (Open Web Text)

Max Activating Token Index: 672

Text #9

Max Range: 3.5485. Min Range: -3.5485

Max Act: 3.3968. Min Act: -0.1700

Data Index: 2385770 (Open Web Text)

Max Activating Token Index: 487

Text #10

Max Range: 3.5485. Min Range: -3.5485

Max Act: 3.3925. Min Act: -0.1700

Data Index: 7419758 (Open Web Text)

Max Activating Token Index: 334

Text #11

Max Range: 3.5485. Min Range: -3.5485

Max Act: 3.3656. Min Act: -0.1700

Data Index: 8391442 (Open Web Text)

Max Activating Token Index: 536

Text #12

Max Range: 3.5485. Min Range: -3.5485

Max Act: 3.3709. Min Act: -0.1700

Data Index: 7698380 (Open Web Text)

Max Activating Token Index: 99

Text #13

Max Range: 3.5485. Min Range: -3.5485

Max Act: 3.4056. Min Act: -0.1700

Data Index: 7736645 (Open Web Text)

Max Activating Token Index: 190

Text #14

Max Range: 3.5485. Min Range: -3.5485

Max Act: 3.3947. Min Act: -0.1700

Data Index: 4005711 (Open Web Text)

Max Activating Token Index: 254

Text #15

Max Range: 3.5485. Min Range: -3.5485

Max Act: 3.3853. Min Act: -0.1700

Data Index: 1733534 (Open Web Text)

Max Activating Token Index: 571

Text #16

Max Range: 3.5485. Min Range: -3.5485

Max Act: 3.3854. Min Act: -0.1700

Data Index: 3055280 (Open Web Text)

Max Activating Token Index: 257

Text #17

Max Range: 3.5485. Min Range: -3.5485

Max Act: 3.3566. Min Act: -0.1700

Data Index: 5044252 (Open Web Text)

Max Activating Token Index: 34

Text #18

Max Range: 3.5485. Min Range: -3.5485

Max Act: 3.3820. Min Act: -0.1700

Data Index: 7301514 (Open Web Text)

Max Activating Token Index: 870

Text #19

Max Range: 3.5485. Min Range: -3.5485

Max Act: 3.3660. Min Act: -0.1700

Data Index: 5270797 (Open Web Text)

Max Activating Token Index: 565