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

Dataset: Open Web Text

Neuron 824 in Layer 5

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: 3.6965. Min Range: -3.6965

Max Act: 3.6965. Min Act: -0.1700

Data Index: 5193355 (Open Web Text)

Max Activating Token Index: 855

Text #1

Max Range: 3.6965. Min Range: -3.6965

Max Act: 3.6751. Min Act: -0.1700

Data Index: 3607397 (Open Web Text)

Max Activating Token Index: 946

Text #2

Max Range: 3.6965. Min Range: -3.6965

Max Act: 3.6731. Min Act: -0.1700

Data Index: 7345950 (Open Web Text)

Max Activating Token Index: 751

Text #3

Max Range: 3.6965. Min Range: -3.6965

Max Act: 3.6416. Min Act: -0.1700

Data Index: 962558 (Open Web Text)

Max Activating Token Index: 859

Text #4

Max Range: 3.6965. Min Range: -3.6965

Max Act: 3.6431. Min Act: -0.1700

Data Index: 3543804 (Open Web Text)

Max Activating Token Index: 269

Text #5

Max Range: 3.6965. Min Range: -3.6965

Max Act: 3.6400. Min Act: -0.1700

Data Index: 2004003 (Open Web Text)

Max Activating Token Index: 756

Text #6

Max Range: 3.6965. Min Range: -3.6965

Max Act: 3.6186. Min Act: -0.1700

Data Index: 8573506 (Open Web Text)

Max Activating Token Index: 1002

Text #7

Max Range: 3.6965. Min Range: -3.6965

Max Act: 3.6271. Min Act: -0.1700

Data Index: 6832343 (Open Web Text)

Max Activating Token Index: 440

Text #8

Max Range: 3.6965. Min Range: -3.6965

Max Act: 3.6023. Min Act: -0.1700

Data Index: 5295321 (Open Web Text)

Max Activating Token Index: 561

Text #9

Max Range: 3.6965. Min Range: -3.6965

Max Act: 3.6152. Min Act: -0.1700

Data Index: 5559047 (Open Web Text)

Max Activating Token Index: 409

Text #10

Max Range: 3.6965. Min Range: -3.6965

Max Act: 3.5976. Min Act: -0.1700

Data Index: 7200026 (Open Web Text)

Max Activating Token Index: 323

Text #11

Max Range: 3.6965. Min Range: -3.6965

Max Act: 3.5873. Min Act: -0.1700

Data Index: 8222908 (Open Web Text)

Max Activating Token Index: 515

Text #12

Max Range: 3.6965. Min Range: -3.6965

Max Act: 3.5875. Min Act: -0.1700

Data Index: 432594 (Open Web Text)

Max Activating Token Index: 725

Text #13

Max Range: 3.6965. Min Range: -3.6965

Max Act: 3.5777. Min Act: -0.1700

Data Index: 4788557 (Open Web Text)

Max Activating Token Index: 764

Text #14

Max Range: 3.6965. Min Range: -3.6965

Max Act: 3.5755. Min Act: -0.1700

Data Index: 7649803 (Open Web Text)

Max Activating Token Index: 966

Text #15

Max Range: 3.6965. Min Range: -3.6965

Max Act: 3.5842. Min Act: -0.1700

Data Index: 7360173 (Open Web Text)

Max Activating Token Index: 676

Text #16

Max Range: 3.6965. Min Range: -3.6965

Max Act: 3.5712. Min Act: -0.1700

Data Index: 3949366 (Open Web Text)

Max Activating Token Index: 64

Text #17

Max Range: 3.6965. Min Range: -3.6965

Max Act: 3.5585. Min Act: -0.1700

Data Index: 7506251 (Open Web Text)

Max Activating Token Index: 241

Text #18

Max Range: 3.6965. Min Range: -3.6965

Max Act: 3.5901. Min Act: -0.1700

Data Index: 447495 (Open Web Text)

Max Activating Token Index: 599

Text #19

Max Range: 3.6965. Min Range: -3.6965

Max Act: 3.5731. Min Act: -0.1700

Data Index: 4592959 (Open Web Text)

Max Activating Token Index: 881