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

Dataset: Open Web Text

Neuron 2553 in Layer 5

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: 4.6620. Min Range: -4.6620

Max Act: 4.6620. Min Act: -0.1700

Data Index: 4791648 (Open Web Text)

Max Activating Token Index: 483

Text #1

Max Range: 4.6620. Min Range: -4.6620

Max Act: 4.6150. Min Act: -0.1700

Data Index: 3584360 (Open Web Text)

Max Activating Token Index: 711

Text #2

Max Range: 4.6620. Min Range: -4.6620

Max Act: 4.4910. Min Act: -0.1700

Data Index: 6276256 (Open Web Text)

Max Activating Token Index: 510

Text #3

Max Range: 4.6620. Min Range: -4.6620

Max Act: 4.4867. Min Act: -0.1700

Data Index: 6688768 (Open Web Text)

Max Activating Token Index: 476

Text #4

Max Range: 4.6620. Min Range: -4.6620

Max Act: 4.5066. Min Act: -0.1700

Data Index: 3230065 (Open Web Text)

Max Activating Token Index: 221

Text #5

Max Range: 4.6620. Min Range: -4.6620

Max Act: 4.4380. Min Act: -0.1700

Data Index: 4811210 (Open Web Text)

Max Activating Token Index: 417

Text #6

Max Range: 4.6620. Min Range: -4.6620

Max Act: 4.4149. Min Act: -0.1700

Data Index: 4931432 (Open Web Text)

Max Activating Token Index: 260

Text #7

Max Range: 4.6620. Min Range: -4.6620

Max Act: 4.3607. Min Act: -0.1700

Data Index: 7270335 (Open Web Text)

Max Activating Token Index: 591

Text #8

Max Range: 4.6620. Min Range: -4.6620

Max Act: 4.3409. Min Act: -0.1700

Data Index: 6035202 (Open Web Text)

Max Activating Token Index: 516

Text #9

Max Range: 4.6620. Min Range: -4.6620

Max Act: 4.3654. Min Act: -0.1700

Data Index: 3556747 (Open Web Text)

Max Activating Token Index: 374

Text #10

Max Range: 4.6620. Min Range: -4.6620

Max Act: 4.3257. Min Act: -0.1700

Data Index: 3807594 (Open Web Text)

Max Activating Token Index: 159

Text #11

Max Range: 4.6620. Min Range: -4.6620

Max Act: 4.3105. Min Act: -0.1700

Data Index: 7315139 (Open Web Text)

Max Activating Token Index: 595

Text #12

Max Range: 4.6620. Min Range: -4.6620

Max Act: 4.3077. Min Act: -0.1700

Data Index: 5307160 (Open Web Text)

Max Activating Token Index: 491

Text #13

Max Range: 4.6620. Min Range: -4.6620

Max Act: 4.3126. Min Act: -0.1700

Data Index: 3148520 (Open Web Text)

Max Activating Token Index: 208

Text #14

Max Range: 4.6620. Min Range: -4.6620

Max Act: 4.2741. Min Act: -0.1700

Data Index: 4885200 (Open Web Text)

Max Activating Token Index: 867

Text #15

Max Range: 4.6620. Min Range: -4.6620

Max Act: 4.2935. Min Act: -0.1700

Data Index: 5092316 (Open Web Text)

Max Activating Token Index: 707

Text #16

Max Range: 4.6620. Min Range: -4.6620

Max Act: 4.3056. Min Act: -0.1700

Data Index: 3147577 (Open Web Text)

Max Activating Token Index: 482

Text #17

Max Range: 4.6620. Min Range: -4.6620

Max Act: 4.2572. Min Act: -0.1700

Data Index: 963873 (Open Web Text)

Max Activating Token Index: 767

Text #18

Max Range: 4.6620. Min Range: -4.6620

Max Act: 4.2427. Min Act: -0.1700

Data Index: 6054675 (Open Web Text)

Max Activating Token Index: 831

Text #19

Max Range: 4.6620. Min Range: -4.6620

Max Act: 4.2545. Min Act: -0.1700

Data Index: 650882 (Open Web Text)

Max Activating Token Index: 584