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

Dataset: Open Web Text

Neuron 2837 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: 3.5457. Min Range: -3.5457

Max Act: 3.5162. Min Act: -0.1700

Data Index: 3992144 (Open Web Text)

Max Activating Token Index: 421

Text #1

Max Range: 3.5457. Min Range: -3.5457

Max Act: 3.5378. Min Act: -0.1700

Data Index: 7611398 (Open Web Text)

Max Activating Token Index: 321

Text #2

Max Range: 3.5457. Min Range: -3.5457

Max Act: 3.5457. Min Act: -0.1700

Data Index: 8025424 (Open Web Text)

Max Activating Token Index: 497

Text #3

Max Range: 3.5457. Min Range: -3.5457

Max Act: 3.4774. Min Act: -0.1700

Data Index: 1876542 (Open Web Text)

Max Activating Token Index: 229

Text #4

Max Range: 3.5457. Min Range: -3.5457

Max Act: 3.4970. Min Act: -0.1700

Data Index: 6387482 (Open Web Text)

Max Activating Token Index: 243

Text #5

Max Range: 3.5457. Min Range: -3.5457

Max Act: 3.4703. Min Act: -0.1700

Data Index: 5022921 (Open Web Text)

Max Activating Token Index: 107

Text #6

Max Range: 3.5457. Min Range: -3.5457

Max Act: 3.4713. Min Act: -0.1700

Data Index: 5118422 (Open Web Text)

Max Activating Token Index: 846

Text #7

Max Range: 3.5457. Min Range: -3.5457

Max Act: 3.4545. Min Act: -0.1700

Data Index: 5756800 (Open Web Text)

Max Activating Token Index: 892

Text #8

Max Range: 3.5457. Min Range: -3.5457

Max Act: 3.4329. Min Act: -0.1700

Data Index: 1295161 (Open Web Text)

Max Activating Token Index: 491

Text #9

Max Range: 3.5457. Min Range: -3.5457

Max Act: 3.4335. Min Act: -0.1700

Data Index: 6248075 (Open Web Text)

Max Activating Token Index: 40

Text #10

Max Range: 3.5457. Min Range: -3.5457

Max Act: 3.4536. Min Act: -0.1700

Data Index: 6927066 (Open Web Text)

Max Activating Token Index: 399

Text #11

Max Range: 3.5457. Min Range: -3.5457

Max Act: 3.4135. Min Act: -0.1700

Data Index: 1471498 (Open Web Text)

Max Activating Token Index: 270

Text #12

Max Range: 3.5457. Min Range: -3.5457

Max Act: 3.4137. Min Act: -0.1700

Data Index: 3936811 (Open Web Text)

Max Activating Token Index: 687

Text #13

Max Range: 3.5457. Min Range: -3.5457

Max Act: 3.4339. Min Act: -0.1700

Data Index: 3706972 (Open Web Text)

Max Activating Token Index: 194

Text #14

Max Range: 3.5457. Min Range: -3.5457

Max Act: 3.4205. Min Act: -0.1700

Data Index: 8084416 (Open Web Text)

Max Activating Token Index: 384

Text #15

Max Range: 3.5457. Min Range: -3.5457

Max Act: 3.4069. Min Act: -0.1700

Data Index: 5042250 (Open Web Text)

Max Activating Token Index: 584

Text #16

Max Range: 3.5457. Min Range: -3.5457

Max Act: 3.4205. Min Act: -0.1700

Data Index: 6699362 (Open Web Text)

Max Activating Token Index: 852

Text #17

Max Range: 3.5457. Min Range: -3.5457

Max Act: 3.4153. Min Act: -0.1700

Data Index: 7481123 (Open Web Text)

Max Activating Token Index: 939

Text #18

Max Range: 3.5457. Min Range: -3.5457

Max Act: 3.3987. Min Act: -0.1700

Data Index: 5398467 (Open Web Text)

Max Activating Token Index: 521

Text #19

Max Range: 3.5457. Min Range: -3.5457

Max Act: 3.3878. Min Act: -0.1700

Data Index: 669410 (Open Web Text)

Max Activating Token Index: 805