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

Dataset: Open Web Text

Neuron 390 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: 3.0296. Min Range: -3.0296

Max Act: 3.0296. Min Act: -0.1700

Data Index: 3428947 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.0296. Min Range: -3.0296

Max Act: 3.0069. Min Act: -0.1700

Data Index: 1234319 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.0296. Min Range: -3.0296

Max Act: 3.0026. Min Act: -0.1700

Data Index: 3297167 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.9659. Min Act: -0.1700

Data Index: 1541227 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.9654. Min Act: -0.1700

Data Index: 6811671 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.9791. Min Act: -0.1700

Data Index: 3879462 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.9577. Min Act: -0.1700

Data Index: 4528539 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.9554. Min Act: -0.1700

Data Index: 5218751 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.9555. Min Act: -0.1700

Data Index: 778067 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.9592. Min Act: -0.1700

Data Index: 5389653 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.9619. Min Act: -0.1700

Data Index: 616253 (Open Web Text)

Max Activating Token Index: 13

Text #11

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.9602. Min Act: -0.1700

Data Index: 6254235 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.9449. Min Act: -0.1700

Data Index: 1990660 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.9395. Min Act: -0.1700

Data Index: 53098 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.9418. Min Act: -0.1700

Data Index: 929859 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.9476. Min Act: -0.1700

Data Index: 646640 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.9378. Min Act: -0.1700

Data Index: 2016684 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.9459. Min Act: -0.1700

Data Index: 2991672 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.9202. Min Act: -0.1700

Data Index: 4353217 (Open Web Text)

Max Activating Token Index: 14

Text #19

Max Range: 3.0296. Min Range: -3.0296

Max Act: 2.9304. Min Act: -0.1700

Data Index: 4459661 (Open Web Text)

Max Activating Token Index: 5