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

Dataset: Open Web Text

Neuron 3014 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: 4.8836. Min Range: -4.8836

Max Act: 4.8836. Min Act: -0.1700

Data Index: 7073915 (Open Web Text)

Max Activating Token Index: 845

Text #1

Max Range: 4.8836. Min Range: -4.8836

Max Act: 4.4422. Min Act: -0.1700

Data Index: 311574 (Open Web Text)

Max Activating Token Index: 412

Text #2

Max Range: 4.8836. Min Range: -4.8836

Max Act: 4.4037. Min Act: -0.1700

Data Index: 6515036 (Open Web Text)

Max Activating Token Index: 121

Text #3

Max Range: 4.8836. Min Range: -4.8836

Max Act: 4.3854. Min Act: -0.1700

Data Index: 2690567 (Open Web Text)

Max Activating Token Index: 375

Text #4

Max Range: 4.8836. Min Range: -4.8836

Max Act: 4.3409. Min Act: -0.1700

Data Index: 746560 (Open Web Text)

Max Activating Token Index: 323

Text #5

Max Range: 4.8836. Min Range: -4.8836

Max Act: 4.3345. Min Act: -0.1700

Data Index: 8402945 (Open Web Text)

Max Activating Token Index: 279

Text #6

Max Range: 4.8836. Min Range: -4.8836

Max Act: 4.3217. Min Act: -0.1700

Data Index: 494379 (Open Web Text)

Max Activating Token Index: 805

Text #7

Max Range: 4.8836. Min Range: -4.8836

Max Act: 4.3084. Min Act: -0.1700

Data Index: 8569873 (Open Web Text)

Max Activating Token Index: 878

Text #8

Max Range: 4.8836. Min Range: -4.8836

Max Act: 4.3136. Min Act: -0.1700

Data Index: 4405634 (Open Web Text)

Max Activating Token Index: 974

Text #9

Max Range: 4.8836. Min Range: -4.8836

Max Act: 4.2953. Min Act: -0.1700

Data Index: 2900056 (Open Web Text)

Max Activating Token Index: 163

Text #10

Max Range: 4.8836. Min Range: -4.8836

Max Act: 4.2785. Min Act: -0.1700

Data Index: 3993117 (Open Web Text)

Max Activating Token Index: 920

Text #11

Max Range: 4.8836. Min Range: -4.8836

Max Act: 4.3261. Min Act: -0.1700

Data Index: 214841 (Open Web Text)

Max Activating Token Index: 410

Text #12

Max Range: 4.8836. Min Range: -4.8836

Max Act: 4.2821. Min Act: -0.1700

Data Index: 1822269 (Open Web Text)

Max Activating Token Index: 826

Text #13

Max Range: 4.8836. Min Range: -4.8836

Max Act: 4.2711. Min Act: -0.1700

Data Index: 3885072 (Open Web Text)

Max Activating Token Index: 221

Text #14

Max Range: 4.8836. Min Range: -4.8836

Max Act: 4.2864. Min Act: -0.1700

Data Index: 1580888 (Open Web Text)

Max Activating Token Index: 735

Text #15

Max Range: 4.8836. Min Range: -4.8836

Max Act: 4.2514. Min Act: -0.1700

Data Index: 853399 (Open Web Text)

Max Activating Token Index: 444

Text #16

Max Range: 4.8836. Min Range: -4.8836

Max Act: 4.2308. Min Act: -0.1700

Data Index: 3867239 (Open Web Text)

Max Activating Token Index: 330

Text #17

Max Range: 4.8836. Min Range: -4.8836

Max Act: 4.2534. Min Act: -0.1700

Data Index: 2641511 (Open Web Text)

Max Activating Token Index: 609

Text #18

Max Range: 4.8836. Min Range: -4.8836

Max Act: 4.2323. Min Act: -0.1700

Data Index: 1502061 (Open Web Text)

Max Activating Token Index: 750

Text #19

Max Range: 4.8836. Min Range: -4.8836

Max Act: 4.2339. Min Act: -0.1700

Data Index: 295270 (Open Web Text)

Max Activating Token Index: 644