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

Dataset: Open Web Text

Neuron 1179 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: 2.9594. Min Range: -2.9594

Max Act: 2.9594. Min Act: -0.1700

Data Index: 2883950 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 2.9594. Min Range: -2.9594

Max Act: 2.9327. Min Act: -0.1700

Data Index: 2705647 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.9594. Min Range: -2.9594

Max Act: 2.9298. Min Act: -0.1700

Data Index: 7160063 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.9594. Min Range: -2.9594

Max Act: 2.8955. Min Act: -0.1700

Data Index: 8473001 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.9594. Min Range: -2.9594

Max Act: 2.8892. Min Act: -0.1700

Data Index: 7435080 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 2.9594. Min Range: -2.9594

Max Act: 2.8713. Min Act: -0.1700

Data Index: 5845407 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 2.9594. Min Range: -2.9594

Max Act: 2.8543. Min Act: -0.1700

Data Index: 5339451 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 2.9594. Min Range: -2.9594

Max Act: 2.8605. Min Act: -0.1700

Data Index: 632539 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 2.9594. Min Range: -2.9594

Max Act: 2.8475. Min Act: -0.1700

Data Index: 3388831 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 2.9594. Min Range: -2.9594

Max Act: 2.8422. Min Act: -0.1700

Data Index: 5834690 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.9594. Min Range: -2.9594

Max Act: 2.8511. Min Act: -0.1700

Data Index: 3706821 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 2.9594. Min Range: -2.9594

Max Act: 2.8465. Min Act: -0.1700

Data Index: 1699340 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.9594. Min Range: -2.9594

Max Act: 2.8351. Min Act: -0.1700

Data Index: 3917680 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 2.9594. Min Range: -2.9594

Max Act: 2.8265. Min Act: -0.1700

Data Index: 5936090 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 2.9594. Min Range: -2.9594

Max Act: 2.8275. Min Act: -0.1700

Data Index: 4133513 (Open Web Text)

Max Activating Token Index: 11

Text #15

Max Range: 2.9594. Min Range: -2.9594

Max Act: 2.8124. Min Act: -0.1700

Data Index: 7790997 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 2.9594. Min Range: -2.9594

Max Act: 2.8152. Min Act: -0.1700

Data Index: 2981996 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.9594. Min Range: -2.9594

Max Act: 2.8180. Min Act: -0.1700

Data Index: 7905076 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 2.9594. Min Range: -2.9594

Max Act: 2.8131. Min Act: -0.1700

Data Index: 3625107 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 2.9594. Min Range: -2.9594

Max Act: 2.8054. Min Act: -0.1700

Data Index: 7435078 (Open Web Text)

Max Activating Token Index: 8