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

Dataset: Open Web Text

Neuron 2972 in Layer 2

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: 3.4418. Min Range: -3.4418

Max Act: 3.4168. Min Act: -0.1700

Data Index: 4928161 (Open Web Text)

Max Activating Token Index: 636

Text #1

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.4418. Min Act: -0.1700

Data Index: 5079628 (Open Web Text)

Max Activating Token Index: 920

Text #2

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.3981. Min Act: -0.1700

Data Index: 7141799 (Open Web Text)

Max Activating Token Index: 280

Text #3

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.3567. Min Act: -0.1700

Data Index: 6988184 (Open Web Text)

Max Activating Token Index: 415

Text #4

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.3656. Min Act: -0.1700

Data Index: 1869108 (Open Web Text)

Max Activating Token Index: 242

Text #5

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.3582. Min Act: -0.1700

Data Index: 6431278 (Open Web Text)

Max Activating Token Index: 834

Text #6

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.3477. Min Act: -0.1700

Data Index: 5503166 (Open Web Text)

Max Activating Token Index: 595

Text #7

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.3431. Min Act: -0.1700

Data Index: 7189083 (Open Web Text)

Max Activating Token Index: 321

Text #8

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.3414. Min Act: -0.1700

Data Index: 339683 (Open Web Text)

Max Activating Token Index: 379

Text #9

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.3031. Min Act: -0.1700

Data Index: 5037353 (Open Web Text)

Max Activating Token Index: 376

Text #10

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.3022. Min Act: -0.1700

Data Index: 7700234 (Open Web Text)

Max Activating Token Index: 1020

Text #11

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2952. Min Act: -0.1700

Data Index: 7148037 (Open Web Text)

Max Activating Token Index: 753

Text #12

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2896. Min Act: -0.1700

Data Index: 4362561 (Open Web Text)

Max Activating Token Index: 709

Text #13

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2748. Min Act: -0.1700

Data Index: 4019816 (Open Web Text)

Max Activating Token Index: 435

Text #14

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2792. Min Act: -0.1700

Data Index: 5249573 (Open Web Text)

Max Activating Token Index: 442

Text #15

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2697. Min Act: -0.1700

Data Index: 2376794 (Open Web Text)

Max Activating Token Index: 809

Text #16

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2628. Min Act: -0.1700

Data Index: 4519197 (Open Web Text)

Max Activating Token Index: 449

Text #17

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2636. Min Act: -0.1700

Data Index: 4657316 (Open Web Text)

Max Activating Token Index: 311

Text #18

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2491. Min Act: -0.1700

Data Index: 2532312 (Open Web Text)

Max Activating Token Index: 984

Text #19

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2411. Min Act: -0.1700

Data Index: 5912102 (Open Web Text)

Max Activating Token Index: 199