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

Dataset: Open Web Text

Neuron 1987 in Layer 6

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: 3.5465. Min Range: -3.5465

Max Act: 3.5465. Min Act: -0.1700

Data Index: 8333837 (Open Web Text)

Max Activating Token Index: 363

Text #1

Max Range: 3.5465. Min Range: -3.5465

Max Act: 3.4043. Min Act: -0.1700

Data Index: 2624838 (Open Web Text)

Max Activating Token Index: 426

Text #2

Max Range: 3.5465. Min Range: -3.5465

Max Act: 3.3577. Min Act: -0.1700

Data Index: 5458226 (Open Web Text)

Max Activating Token Index: 550

Text #3

Max Range: 3.5465. Min Range: -3.5465

Max Act: 3.3673. Min Act: -0.1700

Data Index: 8219971 (Open Web Text)

Max Activating Token Index: 807

Text #4

Max Range: 3.5465. Min Range: -3.5465

Max Act: 3.3637. Min Act: -0.1700

Data Index: 4007650 (Open Web Text)

Max Activating Token Index: 305

Text #5

Max Range: 3.5465. Min Range: -3.5465

Max Act: 3.3396. Min Act: -0.1700

Data Index: 227528 (Open Web Text)

Max Activating Token Index: 854

Text #6

Max Range: 3.5465. Min Range: -3.5465

Max Act: 3.2912. Min Act: -0.1700

Data Index: 1503148 (Open Web Text)

Max Activating Token Index: 73

Text #7

Max Range: 3.5465. Min Range: -3.5465

Max Act: 3.2882. Min Act: -0.1700

Data Index: 4121184 (Open Web Text)

Max Activating Token Index: 173

Text #8

Max Range: 3.5465. Min Range: -3.5465

Max Act: 3.2804. Min Act: -0.1700

Data Index: 1986935 (Open Web Text)

Max Activating Token Index: 640

Text #9

Max Range: 3.5465. Min Range: -3.5465

Max Act: 3.2718. Min Act: -0.1700

Data Index: 2606935 (Open Web Text)

Max Activating Token Index: 596

Text #10

Max Range: 3.5465. Min Range: -3.5465

Max Act: 3.2922. Min Act: -0.1700

Data Index: 8333833 (Open Web Text)

Max Activating Token Index: 540

Text #11

Max Range: 3.5465. Min Range: -3.5465

Max Act: 3.2646. Min Act: -0.1700

Data Index: 5511215 (Open Web Text)

Max Activating Token Index: 597

Text #12

Max Range: 3.5465. Min Range: -3.5465

Max Act: 3.2555. Min Act: -0.1700

Data Index: 7306800 (Open Web Text)

Max Activating Token Index: 783

Text #13

Max Range: 3.5465. Min Range: -3.5465

Max Act: 3.2578. Min Act: -0.1700

Data Index: 6727530 (Open Web Text)

Max Activating Token Index: 397

Text #14

Max Range: 3.5465. Min Range: -3.5465

Max Act: 3.2304. Min Act: -0.1700

Data Index: 1904313 (Open Web Text)

Max Activating Token Index: 750

Text #15

Max Range: 3.5465. Min Range: -3.5465

Max Act: 3.2515. Min Act: -0.1700

Data Index: 6727524 (Open Web Text)

Max Activating Token Index: 83

Text #16

Max Range: 3.5465. Min Range: -3.5465

Max Act: 3.2489. Min Act: -0.1700

Data Index: 1986946 (Open Web Text)

Max Activating Token Index: 818

Text #17

Max Range: 3.5465. Min Range: -3.5465

Max Act: 3.2387. Min Act: -0.1700

Data Index: 1180503 (Open Web Text)

Max Activating Token Index: 650

Text #18

Max Range: 3.5465. Min Range: -3.5465

Max Act: 3.2275. Min Act: -0.1700

Data Index: 4661871 (Open Web Text)

Max Activating Token Index: 624

Text #19

Max Range: 3.5465. Min Range: -3.5465

Max Act: 3.2506. Min Act: -0.1700

Data Index: 6727527 (Open Web Text)

Max Activating Token Index: 570