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

Dataset: Open Web Text

Neuron 680 in Layer 0

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: 4.2816. Min Range: -4.2816

Max Act: 4.2816. Min Act: -0.1700

Data Index: 4987194 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.2816. Min Range: -4.2816

Max Act: 4.1944. Min Act: -0.1700

Data Index: 5725335 (Open Web Text)

Max Activating Token Index: 16

Text #2

Max Range: 4.2816. Min Range: -4.2816

Max Act: 4.1742. Min Act: -0.1700

Data Index: 687503 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 4.2816. Min Range: -4.2816

Max Act: 4.1935. Min Act: -0.1700

Data Index: 1277669 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.2816. Min Range: -4.2816

Max Act: 4.1620. Min Act: -0.1700

Data Index: 5235653 (Open Web Text)

Max Activating Token Index: 14

Text #5

Max Range: 4.2816. Min Range: -4.2816

Max Act: 4.1517. Min Act: -0.1700

Data Index: 7890765 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.2816. Min Range: -4.2816

Max Act: 4.1407. Min Act: -0.1700

Data Index: 8754581 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.2816. Min Range: -4.2816

Max Act: 4.1355. Min Act: -0.1700

Data Index: 2707268 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.2816. Min Range: -4.2816

Max Act: 4.1374. Min Act: -0.1700

Data Index: 1174438 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 4.2816. Min Range: -4.2816

Max Act: 4.1543. Min Act: -0.1700

Data Index: 2938493 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.2816. Min Range: -4.2816

Max Act: 4.1308. Min Act: -0.1700

Data Index: 1030806 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 4.2816. Min Range: -4.2816

Max Act: 4.1350. Min Act: -0.1700

Data Index: 1934065 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.2816. Min Range: -4.2816

Max Act: 4.1488. Min Act: -0.1700

Data Index: 1960535 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 4.2816. Min Range: -4.2816

Max Act: 4.1186. Min Act: -0.1700

Data Index: 3866891 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 4.2816. Min Range: -4.2816

Max Act: 4.1066. Min Act: -0.1700

Data Index: 128716 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 4.2816. Min Range: -4.2816

Max Act: 4.1173. Min Act: -0.1700

Data Index: 2441357 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.2816. Min Range: -4.2816

Max Act: 4.1020. Min Act: -0.1700

Data Index: 6335882 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 4.2816. Min Range: -4.2816

Max Act: 4.1289. Min Act: -0.1700

Data Index: 5793489 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 4.2816. Min Range: -4.2816

Max Act: 4.1253. Min Act: -0.1700

Data Index: 454139 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.2816. Min Range: -4.2816

Max Act: 4.0872. Min Act: -0.1700

Data Index: 6244187 (Open Web Text)

Max Activating Token Index: 4