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

Dataset: Open Web Text

Neuron 7 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: 5.2947. Min Range: -5.2947

Max Act: 5.2947. Min Act: -0.1700

Data Index: 3927339 (Open Web Text)

Max Activating Token Index: 105

Text #1

Max Range: 5.2947. Min Range: -5.2947

Max Act: 4.9816. Min Act: -0.1700

Data Index: 7871800 (Open Web Text)

Max Activating Token Index: 310

Text #2

Max Range: 5.2947. Min Range: -5.2947

Max Act: 4.9825. Min Act: -0.1700

Data Index: 6690092 (Open Web Text)

Max Activating Token Index: 959

Text #3

Max Range: 5.2947. Min Range: -5.2947

Max Act: 4.9021. Min Act: -0.1700

Data Index: 1873996 (Open Web Text)

Max Activating Token Index: 744

Text #4

Max Range: 5.2947. Min Range: -5.2947

Max Act: 4.8563. Min Act: -0.1700

Data Index: 594883 (Open Web Text)

Max Activating Token Index: 511

Text #5

Max Range: 5.2947. Min Range: -5.2947

Max Act: 4.8540. Min Act: -0.1700

Data Index: 2002246 (Open Web Text)

Max Activating Token Index: 689

Text #6

Max Range: 5.2947. Min Range: -5.2947

Max Act: 4.7918. Min Act: -0.1700

Data Index: 5812021 (Open Web Text)

Max Activating Token Index: 858

Text #7

Max Range: 5.2947. Min Range: -5.2947

Max Act: 4.7477. Min Act: -0.1700

Data Index: 5738987 (Open Web Text)

Max Activating Token Index: 507

Text #8

Max Range: 5.2947. Min Range: -5.2947

Max Act: 4.7410. Min Act: -0.1700

Data Index: 1493804 (Open Web Text)

Max Activating Token Index: 737

Text #9

Max Range: 5.2947. Min Range: -5.2947

Max Act: 4.7192. Min Act: -0.1700

Data Index: 1923957 (Open Web Text)

Max Activating Token Index: 766

Text #10

Max Range: 5.2947. Min Range: -5.2947

Max Act: 4.7083. Min Act: -0.1700

Data Index: 2841700 (Open Web Text)

Max Activating Token Index: 516

Text #11

Max Range: 5.2947. Min Range: -5.2947

Max Act: 4.7092. Min Act: -0.1700

Data Index: 5370524 (Open Web Text)

Max Activating Token Index: 770

Text #12

Max Range: 5.2947. Min Range: -5.2947

Max Act: 4.7287. Min Act: -0.1700

Data Index: 1610067 (Open Web Text)

Max Activating Token Index: 777

Text #13

Max Range: 5.2947. Min Range: -5.2947

Max Act: 4.7218. Min Act: -0.1700

Data Index: 5983830 (Open Web Text)

Max Activating Token Index: 200

Text #14

Max Range: 5.2947. Min Range: -5.2947

Max Act: 4.7335. Min Act: -0.1700

Data Index: 819790 (Open Web Text)

Max Activating Token Index: 276

Text #15

Max Range: 5.2947. Min Range: -5.2947

Max Act: 4.6893. Min Act: -0.1700

Data Index: 3752802 (Open Web Text)

Max Activating Token Index: 795

Text #16

Max Range: 5.2947. Min Range: -5.2947

Max Act: 4.6834. Min Act: -0.1700

Data Index: 5502223 (Open Web Text)

Max Activating Token Index: 432

Text #17

Max Range: 5.2947. Min Range: -5.2947

Max Act: 4.7254. Min Act: -0.1700

Data Index: 2551421 (Open Web Text)

Max Activating Token Index: 708

Text #18

Max Range: 5.2947. Min Range: -5.2947

Max Act: 4.7047. Min Act: -0.1700

Data Index: 2417915 (Open Web Text)

Max Activating Token Index: 253

Text #19

Max Range: 5.2947. Min Range: -5.2947

Max Act: 4.7302. Min Act: -0.1700

Data Index: 6323419 (Open Web Text)

Max Activating Token Index: 820