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

Dataset: Open Web Text

Neuron 2081 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: 6.5161. Min Range: -6.5161

Max Act: 6.5161. Min Act: -0.1700

Data Index: 7306871 (Open Web Text)

Max Activating Token Index: 465

Text #1

Max Range: 6.5161. Min Range: -6.5161

Max Act: 6.4325. Min Act: -0.1700

Data Index: 7194311 (Open Web Text)

Max Activating Token Index: 127

Text #2

Max Range: 6.5161. Min Range: -6.5161

Max Act: 6.4451. Min Act: -0.1700

Data Index: 721719 (Open Web Text)

Max Activating Token Index: 661

Text #3

Max Range: 6.5161. Min Range: -6.5161

Max Act: 6.4348. Min Act: -0.1700

Data Index: 5131279 (Open Web Text)

Max Activating Token Index: 382

Text #4

Max Range: 6.5161. Min Range: -6.5161

Max Act: 6.4121. Min Act: -0.1700

Data Index: 813306 (Open Web Text)

Max Activating Token Index: 491

Text #5

Max Range: 6.5161. Min Range: -6.5161

Max Act: 6.4174. Min Act: -0.1700

Data Index: 6347354 (Open Web Text)

Max Activating Token Index: 305

Text #6

Max Range: 6.5161. Min Range: -6.5161

Max Act: 6.4507. Min Act: -0.1700

Data Index: 2940888 (Open Web Text)

Max Activating Token Index: 361

Text #7

Max Range: 6.5161. Min Range: -6.5161

Max Act: 6.3946. Min Act: -0.1700

Data Index: 7947881 (Open Web Text)

Max Activating Token Index: 107

Text #8

Max Range: 6.5161. Min Range: -6.5161

Max Act: 6.3676. Min Act: -0.1700

Data Index: 5803916 (Open Web Text)

Max Activating Token Index: 328

Text #9

Max Range: 6.5161. Min Range: -6.5161

Max Act: 6.3490. Min Act: -0.1700

Data Index: 6412882 (Open Web Text)

Max Activating Token Index: 506

Text #10

Max Range: 6.5161. Min Range: -6.5161

Max Act: 6.2581. Min Act: -0.1700

Data Index: 1841937 (Open Web Text)

Max Activating Token Index: 892

Text #11

Max Range: 6.5161. Min Range: -6.5161

Max Act: 6.2624. Min Act: -0.1700

Data Index: 1657589 (Open Web Text)

Max Activating Token Index: 591

Text #12

Max Range: 6.5161. Min Range: -6.5161

Max Act: 6.2909. Min Act: -0.1700

Data Index: 1464680 (Open Web Text)

Max Activating Token Index: 94

Text #13

Max Range: 6.5161. Min Range: -6.5161

Max Act: 6.2434. Min Act: -0.1700

Data Index: 8492513 (Open Web Text)

Max Activating Token Index: 303

Text #14

Max Range: 6.5161. Min Range: -6.5161

Max Act: 6.2876. Min Act: -0.1700

Data Index: 1982416 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 6.5161. Min Range: -6.5161

Max Act: 6.2550. Min Act: -0.1700

Data Index: 8540924 (Open Web Text)

Max Activating Token Index: 769

Text #16

Max Range: 6.5161. Min Range: -6.5161

Max Act: 6.3022. Min Act: -0.1700

Data Index: 5724368 (Open Web Text)

Max Activating Token Index: 497

Text #17

Max Range: 6.5161. Min Range: -6.5161

Max Act: 6.2279. Min Act: -0.1700

Data Index: 7404892 (Open Web Text)

Max Activating Token Index: 539

Text #18

Max Range: 6.5161. Min Range: -6.5161

Max Act: 6.2503. Min Act: -0.1700

Data Index: 4116702 (Open Web Text)

Max Activating Token Index: 317

Text #19

Max Range: 6.5161. Min Range: -6.5161

Max Act: 6.2505. Min Act: -0.1700

Data Index: 1028500 (Open Web Text)

Max Activating Token Index: 680