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

Dataset: Open Web Text

Neuron 86 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: 3.3950. Min Range: -3.3950

Max Act: 3.3753. Min Act: -0.1700

Data Index: 6852307 (Open Web Text)

Max Activating Token Index: 297

Text #1

Max Range: 3.3950. Min Range: -3.3950

Max Act: 3.3950. Min Act: -0.1700

Data Index: 7183989 (Open Web Text)

Max Activating Token Index: 478

Text #2

Max Range: 3.3950. Min Range: -3.3950

Max Act: 3.3295. Min Act: -0.1700

Data Index: 7825117 (Open Web Text)

Max Activating Token Index: 535

Text #3

Max Range: 3.3950. Min Range: -3.3950

Max Act: 3.2936. Min Act: -0.1700

Data Index: 1705954 (Open Web Text)

Max Activating Token Index: 602

Text #4

Max Range: 3.3950. Min Range: -3.3950

Max Act: 3.2705. Min Act: -0.1700

Data Index: 1527257 (Open Web Text)

Max Activating Token Index: 406

Text #5

Max Range: 3.3950. Min Range: -3.3950

Max Act: 3.2686. Min Act: -0.1700

Data Index: 5355745 (Open Web Text)

Max Activating Token Index: 926

Text #6

Max Range: 3.3950. Min Range: -3.3950

Max Act: 3.2894. Min Act: -0.1700

Data Index: 8257337 (Open Web Text)

Max Activating Token Index: 562

Text #7

Max Range: 3.3950. Min Range: -3.3950

Max Act: 3.2427. Min Act: -0.1700

Data Index: 5765743 (Open Web Text)

Max Activating Token Index: 514

Text #8

Max Range: 3.3950. Min Range: -3.3950

Max Act: 3.1964. Min Act: -0.1700

Data Index: 6886031 (Open Web Text)

Max Activating Token Index: 924

Text #9

Max Range: 3.3950. Min Range: -3.3950

Max Act: 3.2048. Min Act: -0.1700

Data Index: 4707106 (Open Web Text)

Max Activating Token Index: 366

Text #10

Max Range: 3.3950. Min Range: -3.3950

Max Act: 3.2215. Min Act: -0.1700

Data Index: 8546048 (Open Web Text)

Max Activating Token Index: 392

Text #11

Max Range: 3.3950. Min Range: -3.3950

Max Act: 3.2430. Min Act: -0.1700

Data Index: 1546935 (Open Web Text)

Max Activating Token Index: 540

Text #12

Max Range: 3.3950. Min Range: -3.3950

Max Act: 3.1795. Min Act: -0.1700

Data Index: 2718122 (Open Web Text)

Max Activating Token Index: 852

Text #13

Max Range: 3.3950. Min Range: -3.3950

Max Act: 3.2121. Min Act: -0.1700

Data Index: 2422697 (Open Web Text)

Max Activating Token Index: 941

Text #14

Max Range: 3.3950. Min Range: -3.3950

Max Act: 3.2104. Min Act: -0.1700

Data Index: 7576770 (Open Web Text)

Max Activating Token Index: 406

Text #15

Max Range: 3.3950. Min Range: -3.3950

Max Act: 3.1711. Min Act: -0.1700

Data Index: 35034 (Open Web Text)

Max Activating Token Index: 824

Text #16

Max Range: 3.3950. Min Range: -3.3950

Max Act: 3.1659. Min Act: -0.1700

Data Index: 2919578 (Open Web Text)

Max Activating Token Index: 973

Text #17

Max Range: 3.3950. Min Range: -3.3950

Max Act: 3.1943. Min Act: -0.1700

Data Index: 2745434 (Open Web Text)

Max Activating Token Index: 763

Text #18

Max Range: 3.3950. Min Range: -3.3950

Max Act: 3.1567. Min Act: -0.1700

Data Index: 3208053 (Open Web Text)

Max Activating Token Index: 804

Text #19

Max Range: 3.3950. Min Range: -3.3950

Max Act: 3.2152. Min Act: -0.1700

Data Index: 6209228 (Open Web Text)

Max Activating Token Index: 498