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

Dataset: Open Web Text

Neuron 2716 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: 3.5301. Min Range: -3.5301

Max Act: 3.5301. Min Act: -0.1700

Data Index: 3622281 (Open Web Text)

Max Activating Token Index: 599

Text #1

Max Range: 3.5301. Min Range: -3.5301

Max Act: 3.4976. Min Act: -0.1700

Data Index: 5910409 (Open Web Text)

Max Activating Token Index: 860

Text #2

Max Range: 3.5301. Min Range: -3.5301

Max Act: 3.4483. Min Act: -0.1700

Data Index: 58472 (Open Web Text)

Max Activating Token Index: 28

Text #3

Max Range: 3.5301. Min Range: -3.5301

Max Act: 3.4074. Min Act: -0.1700

Data Index: 4787410 (Open Web Text)

Max Activating Token Index: 466

Text #4

Max Range: 3.5301. Min Range: -3.5301

Max Act: 3.4048. Min Act: -0.1700

Data Index: 4267570 (Open Web Text)

Max Activating Token Index: 25

Text #5

Max Range: 3.5301. Min Range: -3.5301

Max Act: 3.3574. Min Act: -0.1700

Data Index: 2361564 (Open Web Text)

Max Activating Token Index: 595

Text #6

Max Range: 3.5301. Min Range: -3.5301

Max Act: 3.3777. Min Act: -0.1700

Data Index: 8551188 (Open Web Text)

Max Activating Token Index: 293

Text #7

Max Range: 3.5301. Min Range: -3.5301

Max Act: 3.3534. Min Act: -0.1700

Data Index: 1010297 (Open Web Text)

Max Activating Token Index: 19

Text #8

Max Range: 3.5301. Min Range: -3.5301

Max Act: 3.3304. Min Act: -0.1700

Data Index: 7460478 (Open Web Text)

Max Activating Token Index: 707

Text #9

Max Range: 3.5301. Min Range: -3.5301

Max Act: 3.3087. Min Act: -0.1700

Data Index: 2900955 (Open Web Text)

Max Activating Token Index: 39

Text #10

Max Range: 3.5301. Min Range: -3.5301

Max Act: 3.3132. Min Act: -0.1700

Data Index: 7973602 (Open Web Text)

Max Activating Token Index: 606

Text #11

Max Range: 3.5301. Min Range: -3.5301

Max Act: 3.3214. Min Act: -0.1700

Data Index: 5700999 (Open Web Text)

Max Activating Token Index: 128

Text #12

Max Range: 3.5301. Min Range: -3.5301

Max Act: 3.2993. Min Act: -0.1700

Data Index: 6238585 (Open Web Text)

Max Activating Token Index: 580

Text #13

Max Range: 3.5301. Min Range: -3.5301

Max Act: 3.2762. Min Act: -0.1700

Data Index: 8498181 (Open Web Text)

Max Activating Token Index: 580

Text #14

Max Range: 3.5301. Min Range: -3.5301

Max Act: 3.3017. Min Act: -0.1700

Data Index: 3430451 (Open Web Text)

Max Activating Token Index: 481

Text #15

Max Range: 3.5301. Min Range: -3.5301

Max Act: 3.2605. Min Act: -0.1700

Data Index: 8214923 (Open Web Text)

Max Activating Token Index: 524

Text #16

Max Range: 3.5301. Min Range: -3.5301

Max Act: 3.2765. Min Act: -0.1700

Data Index: 2790936 (Open Web Text)

Max Activating Token Index: 137

Text #17

Max Range: 3.5301. Min Range: -3.5301

Max Act: 3.2568. Min Act: -0.1700

Data Index: 7737508 (Open Web Text)

Max Activating Token Index: 567

Text #18

Max Range: 3.5301. Min Range: -3.5301

Max Act: 3.2589. Min Act: -0.1700

Data Index: 5885799 (Open Web Text)

Max Activating Token Index: 30

Text #19

Max Range: 3.5301. Min Range: -3.5301

Max Act: 3.2617. Min Act: -0.1700

Data Index: 1171120 (Open Web Text)

Max Activating Token Index: 19