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

Dataset: Open Web Text

Neuron 970 in Layer 4

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: 3.7454. Min Range: -3.7454

Max Act: 3.7454. Min Act: -0.1700

Data Index: 6206055 (Open Web Text)

Max Activating Token Index: 84

Text #1

Max Range: 3.7454. Min Range: -3.7454

Max Act: 3.6598. Min Act: -0.1700

Data Index: 8396393 (Open Web Text)

Max Activating Token Index: 1000

Text #2

Max Range: 3.7454. Min Range: -3.7454

Max Act: 3.6450. Min Act: -0.1700

Data Index: 6343256 (Open Web Text)

Max Activating Token Index: 150

Text #3

Max Range: 3.7454. Min Range: -3.7454

Max Act: 3.6315. Min Act: -0.1700

Data Index: 3645328 (Open Web Text)

Max Activating Token Index: 983

Text #4

Max Range: 3.7454. Min Range: -3.7454

Max Act: 3.6411. Min Act: -0.1700

Data Index: 4391618 (Open Web Text)

Max Activating Token Index: 1017

Text #5

Max Range: 3.7454. Min Range: -3.7454

Max Act: 3.6097. Min Act: -0.1700

Data Index: 6131213 (Open Web Text)

Max Activating Token Index: 410

Text #6

Max Range: 3.7454. Min Range: -3.7454

Max Act: 3.5940. Min Act: -0.1700

Data Index: 8402434 (Open Web Text)

Max Activating Token Index: 510

Text #7

Max Range: 3.7454. Min Range: -3.7454

Max Act: 3.6020. Min Act: -0.1700

Data Index: 6684871 (Open Web Text)

Max Activating Token Index: 150

Text #8

Max Range: 3.7454. Min Range: -3.7454

Max Act: 3.5820. Min Act: -0.1700

Data Index: 8439276 (Open Web Text)

Max Activating Token Index: 1003

Text #9

Max Range: 3.7454. Min Range: -3.7454

Max Act: 3.6082. Min Act: -0.1700

Data Index: 142621 (Open Web Text)

Max Activating Token Index: 589

Text #10

Max Range: 3.7454. Min Range: -3.7454

Max Act: 3.5531. Min Act: -0.1700

Data Index: 3477034 (Open Web Text)

Max Activating Token Index: 522

Text #11

Max Range: 3.7454. Min Range: -3.7454

Max Act: 3.5633. Min Act: -0.1700

Data Index: 8676969 (Open Web Text)

Max Activating Token Index: 401

Text #12

Max Range: 3.7454. Min Range: -3.7454

Max Act: 3.5614. Min Act: -0.1700

Data Index: 3173265 (Open Web Text)

Max Activating Token Index: 30

Text #13

Max Range: 3.7454. Min Range: -3.7454

Max Act: 3.5521. Min Act: -0.1700

Data Index: 6758058 (Open Web Text)

Max Activating Token Index: 14

Text #14

Max Range: 3.7454. Min Range: -3.7454

Max Act: 3.5499. Min Act: -0.1700

Data Index: 8745809 (Open Web Text)

Max Activating Token Index: 575

Text #15

Max Range: 3.7454. Min Range: -3.7454

Max Act: 3.5348. Min Act: -0.1700

Data Index: 4987620 (Open Web Text)

Max Activating Token Index: 405

Text #16

Max Range: 3.7454. Min Range: -3.7454

Max Act: 3.5615. Min Act: -0.1700

Data Index: 3721246 (Open Web Text)

Max Activating Token Index: 538

Text #17

Max Range: 3.7454. Min Range: -3.7454

Max Act: 3.5542. Min Act: -0.1700

Data Index: 6248959 (Open Web Text)

Max Activating Token Index: 61

Text #18

Max Range: 3.7454. Min Range: -3.7454

Max Act: 3.5365. Min Act: -0.1700

Data Index: 1449245 (Open Web Text)

Max Activating Token Index: 475

Text #19

Max Range: 3.7454. Min Range: -3.7454

Max Act: 3.5382. Min Act: -0.1700

Data Index: 3351031 (Open Web Text)

Max Activating Token Index: 773