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

Dataset: Open Web Text

Neuron 1266 in Layer 6

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: 5.9618. Min Range: -5.9618

Max Act: 5.9618. Min Act: -0.1700

Data Index: 6844166 (Open Web Text)

Max Activating Token Index: 433

Text #1

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.6179. Min Act: -0.1700

Data Index: 4696566 (Open Web Text)

Max Activating Token Index: 215

Text #2

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.4465. Min Act: -0.1700

Data Index: 4676861 (Open Web Text)

Max Activating Token Index: 849

Text #3

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.3951. Min Act: -0.1700

Data Index: 2484532 (Open Web Text)

Max Activating Token Index: 217

Text #4

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.4089. Min Act: -0.1700

Data Index: 5118457 (Open Web Text)

Max Activating Token Index: 857

Text #5

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.4421. Min Act: -0.1700

Data Index: 1368537 (Open Web Text)

Max Activating Token Index: 335

Text #6

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.4089. Min Act: -0.1700

Data Index: 6442749 (Open Web Text)

Max Activating Token Index: 732

Text #7

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.4129. Min Act: -0.1700

Data Index: 485810 (Open Web Text)

Max Activating Token Index: 433

Text #8

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.3970. Min Act: -0.1700

Data Index: 8240671 (Open Web Text)

Max Activating Token Index: 400

Text #9

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.3856. Min Act: -0.1700

Data Index: 3407334 (Open Web Text)

Max Activating Token Index: 692

Text #10

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.3644. Min Act: -0.1700

Data Index: 2886567 (Open Web Text)

Max Activating Token Index: 608

Text #11

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.3831. Min Act: -0.1700

Data Index: 3366901 (Open Web Text)

Max Activating Token Index: 905

Text #12

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.3424. Min Act: -0.1700

Data Index: 4997859 (Open Web Text)

Max Activating Token Index: 930

Text #13

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.3688. Min Act: -0.1700

Data Index: 6965855 (Open Web Text)

Max Activating Token Index: 963

Text #14

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.3138. Min Act: -0.1700

Data Index: 5008646 (Open Web Text)

Max Activating Token Index: 278

Text #15

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.2722. Min Act: -0.1700

Data Index: 5320718 (Open Web Text)

Max Activating Token Index: 288

Text #16

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.3013. Min Act: -0.1700

Data Index: 2544216 (Open Web Text)

Max Activating Token Index: 741

Text #17

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.3403. Min Act: -0.1700

Data Index: 300449 (Open Web Text)

Max Activating Token Index: 864

Text #18

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.3186. Min Act: -0.1700

Data Index: 7278996 (Open Web Text)

Max Activating Token Index: 805

Text #19

Max Range: 5.9618. Min Range: -5.9618

Max Act: 5.2473. Min Act: -0.1700

Data Index: 1937445 (Open Web Text)

Max Activating Token Index: 680