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

Dataset: Open Web Text

Neuron 3030 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: 3.0395. Min Range: -3.0395

Max Act: 3.0395. Min Act: -0.1700

Data Index: 7173609 (Open Web Text)

Max Activating Token Index: 17

Text #1

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.9845. Min Act: -0.1700

Data Index: 2644126 (Open Web Text)

Max Activating Token Index: 228

Text #2

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.9864. Min Act: -0.1700

Data Index: 3797230 (Open Web Text)

Max Activating Token Index: 439

Text #3

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.9700. Min Act: -0.1700

Data Index: 9950 (Open Web Text)

Max Activating Token Index: 641

Text #4

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.9955. Min Act: -0.1700

Data Index: 5330804 (Open Web Text)

Max Activating Token Index: 530

Text #5

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.9809. Min Act: -0.1700

Data Index: 7134713 (Open Web Text)

Max Activating Token Index: 377

Text #6

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.9593. Min Act: -0.1700

Data Index: 2785696 (Open Web Text)

Max Activating Token Index: 1022

Text #7

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.9636. Min Act: -0.1700

Data Index: 6742084 (Open Web Text)

Max Activating Token Index: 448

Text #8

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.9433. Min Act: -0.1700

Data Index: 4015426 (Open Web Text)

Max Activating Token Index: 65

Text #9

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.9096. Min Act: -0.1700

Data Index: 6871661 (Open Web Text)

Max Activating Token Index: 347

Text #10

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.8940. Min Act: -0.1700

Data Index: 8669297 (Open Web Text)

Max Activating Token Index: 373

Text #11

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.8895. Min Act: -0.1700

Data Index: 1368302 (Open Web Text)

Max Activating Token Index: 947

Text #12

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.8899. Min Act: -0.1700

Data Index: 5296738 (Open Web Text)

Max Activating Token Index: 206

Text #13

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.9030. Min Act: -0.1700

Data Index: 5302244 (Open Web Text)

Max Activating Token Index: 833

Text #14

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.8958. Min Act: -0.1700

Data Index: 5434208 (Open Web Text)

Max Activating Token Index: 70

Text #15

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.8883. Min Act: -0.1700

Data Index: 8067065 (Open Web Text)

Max Activating Token Index: 484

Text #16

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.9121. Min Act: -0.1700

Data Index: 4762654 (Open Web Text)

Max Activating Token Index: 560

Text #17

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.8897. Min Act: -0.1700

Data Index: 4169551 (Open Web Text)

Max Activating Token Index: 850

Text #18

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.8930. Min Act: -0.1700

Data Index: 5027947 (Open Web Text)

Max Activating Token Index: 994

Text #19

Max Range: 3.0395. Min Range: -3.0395

Max Act: 2.8767. Min Act: -0.1700

Data Index: 5224108 (Open Web Text)

Max Activating Token Index: 400