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

Dataset: Open Web Text

Neuron 869 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: 4.6203. Min Range: -4.6203

Max Act: 4.6203. Min Act: -0.1700

Data Index: 7251734 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.6203. Min Range: -4.6203

Max Act: 4.5843. Min Act: -0.1700

Data Index: 7821614 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.6203. Min Range: -4.6203

Max Act: 4.5365. Min Act: -0.1700

Data Index: 4851923 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 4.6203. Min Range: -4.6203

Max Act: 4.5378. Min Act: -0.1700

Data Index: 6878750 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 4.6203. Min Range: -4.6203

Max Act: 4.4944. Min Act: -0.1700

Data Index: 3507296 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 4.6203. Min Range: -4.6203

Max Act: 4.4612. Min Act: -0.1700

Data Index: 1551334 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.6203. Min Range: -4.6203

Max Act: 4.4642. Min Act: -0.1700

Data Index: 3629577 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.6203. Min Range: -4.6203

Max Act: 4.4665. Min Act: -0.1700

Data Index: 1529435 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 4.6203. Min Range: -4.6203

Max Act: 4.4575. Min Act: -0.1700

Data Index: 8186056 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.6203. Min Range: -4.6203

Max Act: 4.4646. Min Act: -0.1700

Data Index: 2727088 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 4.6203. Min Range: -4.6203

Max Act: 4.4646. Min Act: -0.1700

Data Index: 3706604 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 4.6203. Min Range: -4.6203

Max Act: 4.4646. Min Act: -0.1700

Data Index: 1918645 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 4.6203. Min Range: -4.6203

Max Act: 4.4667. Min Act: -0.1700

Data Index: 321655 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 4.6203. Min Range: -4.6203

Max Act: 4.4217. Min Act: -0.1700

Data Index: 4869390 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.6203. Min Range: -4.6203

Max Act: 4.4472. Min Act: -0.1700

Data Index: 8683859 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.6203. Min Range: -4.6203

Max Act: 4.4348. Min Act: -0.1700

Data Index: 3501263 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.6203. Min Range: -4.6203

Max Act: 4.4316. Min Act: -0.1700

Data Index: 1835135 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.6203. Min Range: -4.6203

Max Act: 4.4398. Min Act: -0.1700

Data Index: 3529516 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 4.6203. Min Range: -4.6203

Max Act: 4.4281. Min Act: -0.1700

Data Index: 4121333 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.6203. Min Range: -4.6203

Max Act: 4.4475. Min Act: -0.1700

Data Index: 3941422 (Open Web Text)

Max Activating Token Index: 3