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

Dataset: Open Web Text

Neuron 1458 in Layer 1

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: 4.4493. Min Range: -4.4493

Max Act: 4.4493. Min Act: -0.1700

Data Index: 2537283 (Open Web Text)

Max Activating Token Index: 920

Text #1

Max Range: 4.4493. Min Range: -4.4493

Max Act: 4.4319. Min Act: -0.1700

Data Index: 5011611 (Open Web Text)

Max Activating Token Index: 72

Text #2

Max Range: 4.4493. Min Range: -4.4493

Max Act: 4.4353. Min Act: -0.1700

Data Index: 4906739 (Open Web Text)

Max Activating Token Index: 848

Text #3

Max Range: 4.4493. Min Range: -4.4493

Max Act: 4.4214. Min Act: -0.1700

Data Index: 8238625 (Open Web Text)

Max Activating Token Index: 501

Text #4

Max Range: 4.4493. Min Range: -4.4493

Max Act: 4.4186. Min Act: -0.1700

Data Index: 3191926 (Open Web Text)

Max Activating Token Index: 589

Text #5

Max Range: 4.4493. Min Range: -4.4493

Max Act: 4.4430. Min Act: -0.1700

Data Index: 8725216 (Open Web Text)

Max Activating Token Index: 126

Text #6

Max Range: 4.4493. Min Range: -4.4493

Max Act: 4.4485. Min Act: -0.1700

Data Index: 5382331 (Open Web Text)

Max Activating Token Index: 591

Text #7

Max Range: 4.4493. Min Range: -4.4493

Max Act: 4.4133. Min Act: -0.1700

Data Index: 5655692 (Open Web Text)

Max Activating Token Index: 952

Text #8

Max Range: 4.4493. Min Range: -4.4493

Max Act: 4.4083. Min Act: -0.1700

Data Index: 1614940 (Open Web Text)

Max Activating Token Index: 661

Text #9

Max Range: 4.4493. Min Range: -4.4493

Max Act: 4.4111. Min Act: -0.1700

Data Index: 8366981 (Open Web Text)

Max Activating Token Index: 563

Text #10

Max Range: 4.4493. Min Range: -4.4493

Max Act: 4.4044. Min Act: -0.1700

Data Index: 8009858 (Open Web Text)

Max Activating Token Index: 1012

Text #11

Max Range: 4.4493. Min Range: -4.4493

Max Act: 4.3934. Min Act: -0.1700

Data Index: 3951314 (Open Web Text)

Max Activating Token Index: 505

Text #12

Max Range: 4.4493. Min Range: -4.4493

Max Act: 4.3819. Min Act: -0.1700

Data Index: 202838 (Open Web Text)

Max Activating Token Index: 133

Text #13

Max Range: 4.4493. Min Range: -4.4493

Max Act: 4.3886. Min Act: -0.1700

Data Index: 6633300 (Open Web Text)

Max Activating Token Index: 955

Text #14

Max Range: 4.4493. Min Range: -4.4493

Max Act: 4.3591. Min Act: -0.1700

Data Index: 631501 (Open Web Text)

Max Activating Token Index: 327

Text #15

Max Range: 4.4493. Min Range: -4.4493

Max Act: 4.3865. Min Act: -0.1700

Data Index: 8312658 (Open Web Text)

Max Activating Token Index: 595

Text #16

Max Range: 4.4493. Min Range: -4.4493

Max Act: 4.3698. Min Act: -0.1700

Data Index: 4952881 (Open Web Text)

Max Activating Token Index: 322

Text #17

Max Range: 4.4493. Min Range: -4.4493

Max Act: 4.3765. Min Act: -0.1700

Data Index: 8191443 (Open Web Text)

Max Activating Token Index: 82

Text #18

Max Range: 4.4493. Min Range: -4.4493

Max Act: 4.3895. Min Act: -0.1700

Data Index: 4952882 (Open Web Text)

Max Activating Token Index: 553

Text #19

Max Range: 4.4493. Min Range: -4.4493

Max Act: 4.3923. Min Act: -0.1700

Data Index: 3270100 (Open Web Text)

Max Activating Token Index: 460