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

Dataset: Open Web Text

Neuron 633 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: 4.8690. Min Range: -4.8690

Max Act: 4.8690. Min Act: -0.1700

Data Index: 7287377 (Open Web Text)

Max Activating Token Index: 299

Text #1

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.7205. Min Act: -0.1700

Data Index: 7149832 (Open Web Text)

Max Activating Token Index: 810

Text #2

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.7041. Min Act: -0.1700

Data Index: 8801825 (Open Web Text)

Max Activating Token Index: 875

Text #3

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.5919. Min Act: -0.1700

Data Index: 3956921 (Open Web Text)

Max Activating Token Index: 977

Text #4

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.6241. Min Act: -0.1700

Data Index: 6113233 (Open Web Text)

Max Activating Token Index: 931

Text #5

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.5229. Min Act: -0.1700

Data Index: 1516608 (Open Web Text)

Max Activating Token Index: 603

Text #6

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.4956. Min Act: -0.1700

Data Index: 603471 (Open Web Text)

Max Activating Token Index: 915

Text #7

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.4499. Min Act: -0.1700

Data Index: 8318615 (Open Web Text)

Max Activating Token Index: 282

Text #8

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.4692. Min Act: -0.1700

Data Index: 7381053 (Open Web Text)

Max Activating Token Index: 194

Text #9

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.5332. Min Act: -0.1700

Data Index: 4286715 (Open Web Text)

Max Activating Token Index: 101

Text #10

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.4803. Min Act: -0.1700

Data Index: 8051835 (Open Web Text)

Max Activating Token Index: 128

Text #11

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.5107. Min Act: -0.1700

Data Index: 3200167 (Open Web Text)

Max Activating Token Index: 463

Text #12

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.4590. Min Act: -0.1700

Data Index: 5465992 (Open Web Text)

Max Activating Token Index: 832

Text #13

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.4177. Min Act: -0.1700

Data Index: 2137441 (Open Web Text)

Max Activating Token Index: 301

Text #14

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.4559. Min Act: -0.1700

Data Index: 674231 (Open Web Text)

Max Activating Token Index: 725

Text #15

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.4437. Min Act: -0.1700

Data Index: 1072048 (Open Web Text)

Max Activating Token Index: 356

Text #16

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.4322. Min Act: -0.1700

Data Index: 8164424 (Open Web Text)

Max Activating Token Index: 108

Text #17

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.4321. Min Act: -0.1700

Data Index: 7389682 (Open Web Text)

Max Activating Token Index: 817

Text #18

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.3607. Min Act: -0.1700

Data Index: 2736606 (Open Web Text)

Max Activating Token Index: 940

Text #19

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.4168. Min Act: -0.1700

Data Index: 6546697 (Open Web Text)

Max Activating Token Index: 708