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

Dataset: Open Web Text

Neuron 1773 in Layer 3

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: 5.6217. Min Range: -5.6217

Max Act: 5.5814. Min Act: -0.1700

Data Index: 7203003 (Open Web Text)

Max Activating Token Index: 632

Text #1

Max Range: 5.6217. Min Range: -5.6217

Max Act: 5.6217. Min Act: -0.1700

Data Index: 3448929 (Open Web Text)

Max Activating Token Index: 897

Text #2

Max Range: 5.6217. Min Range: -5.6217

Max Act: 5.5291. Min Act: -0.1700

Data Index: 4960846 (Open Web Text)

Max Activating Token Index: 17

Text #3

Max Range: 5.6217. Min Range: -5.6217

Max Act: 5.4834. Min Act: -0.1700

Data Index: 6031118 (Open Web Text)

Max Activating Token Index: 34

Text #4

Max Range: 5.6217. Min Range: -5.6217

Max Act: 5.4755. Min Act: -0.1700

Data Index: 1563632 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 5.6217. Min Range: -5.6217

Max Act: 5.4688. Min Act: -0.1700

Data Index: 4201091 (Open Web Text)

Max Activating Token Index: 420

Text #6

Max Range: 5.6217. Min Range: -5.6217

Max Act: 5.4709. Min Act: -0.1700

Data Index: 7085994 (Open Web Text)

Max Activating Token Index: 53

Text #7

Max Range: 5.6217. Min Range: -5.6217

Max Act: 5.4629. Min Act: -0.1700

Data Index: 8429081 (Open Web Text)

Max Activating Token Index: 353

Text #8

Max Range: 5.6217. Min Range: -5.6217

Max Act: 5.4869. Min Act: -0.1700

Data Index: 6485661 (Open Web Text)

Max Activating Token Index: 762

Text #9

Max Range: 5.6217. Min Range: -5.6217

Max Act: 5.4606. Min Act: -0.1700

Data Index: 3030386 (Open Web Text)

Max Activating Token Index: 57

Text #10

Max Range: 5.6217. Min Range: -5.6217

Max Act: 5.4170. Min Act: -0.1700

Data Index: 7175731 (Open Web Text)

Max Activating Token Index: 32

Text #11

Max Range: 5.6217. Min Range: -5.6217

Max Act: 5.3817. Min Act: -0.1700

Data Index: 6448205 (Open Web Text)

Max Activating Token Index: 42

Text #12

Max Range: 5.6217. Min Range: -5.6217

Max Act: 5.3676. Min Act: -0.1700

Data Index: 4778696 (Open Web Text)

Max Activating Token Index: 30

Text #13

Max Range: 5.6217. Min Range: -5.6217

Max Act: 5.3634. Min Act: -0.1700

Data Index: 256529 (Open Web Text)

Max Activating Token Index: 424

Text #14

Max Range: 5.6217. Min Range: -5.6217

Max Act: 5.3890. Min Act: -0.1700

Data Index: 4275489 (Open Web Text)

Max Activating Token Index: 465

Text #15

Max Range: 5.6217. Min Range: -5.6217

Max Act: 5.3893. Min Act: -0.1700

Data Index: 4290406 (Open Web Text)

Max Activating Token Index: 977

Text #16

Max Range: 5.6217. Min Range: -5.6217

Max Act: 5.3885. Min Act: -0.1700

Data Index: 3432207 (Open Web Text)

Max Activating Token Index: 384

Text #17

Max Range: 5.6217. Min Range: -5.6217

Max Act: 5.3674. Min Act: -0.1700

Data Index: 8590823 (Open Web Text)

Max Activating Token Index: 459

Text #18

Max Range: 5.6217. Min Range: -5.6217

Max Act: 5.3636. Min Act: -0.1700

Data Index: 3000953 (Open Web Text)

Max Activating Token Index: 838

Text #19

Max Range: 5.6217. Min Range: -5.6217

Max Act: 5.3444. Min Act: -0.1700

Data Index: 783398 (Open Web Text)

Max Activating Token Index: 34