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

Dataset: Open Web Text

Neuron 1570 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: 4.7424. Min Range: -4.7424

Max Act: 4.7424. Min Act: -0.1700

Data Index: 7841355 (Open Web Text)

Max Activating Token Index: 593

Text #1

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.5550. Min Act: -0.1700

Data Index: 8764280 (Open Web Text)

Max Activating Token Index: 479

Text #2

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.5436. Min Act: -0.1700

Data Index: 7021587 (Open Web Text)

Max Activating Token Index: 664

Text #3

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.5266. Min Act: -0.1700

Data Index: 5890633 (Open Web Text)

Max Activating Token Index: 892

Text #4

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.5269. Min Act: -0.1700

Data Index: 6614330 (Open Web Text)

Max Activating Token Index: 172

Text #5

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.4364. Min Act: -0.1700

Data Index: 5098692 (Open Web Text)

Max Activating Token Index: 366

Text #6

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.4321. Min Act: -0.1700

Data Index: 7254874 (Open Web Text)

Max Activating Token Index: 257

Text #7

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.4117. Min Act: -0.1700

Data Index: 2214656 (Open Web Text)

Max Activating Token Index: 162

Text #8

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.4032. Min Act: -0.1700

Data Index: 6630905 (Open Web Text)

Max Activating Token Index: 405

Text #9

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.3999. Min Act: -0.1700

Data Index: 1286108 (Open Web Text)

Max Activating Token Index: 567

Text #10

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.4109. Min Act: -0.1700

Data Index: 445088 (Open Web Text)

Max Activating Token Index: 363

Text #11

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.3901. Min Act: -0.1700

Data Index: 1254741 (Open Web Text)

Max Activating Token Index: 440

Text #12

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.3349. Min Act: -0.1700

Data Index: 3040785 (Open Web Text)

Max Activating Token Index: 63

Text #13

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.3238. Min Act: -0.1700

Data Index: 1437153 (Open Web Text)

Max Activating Token Index: 738

Text #14

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.3153. Min Act: -0.1700

Data Index: 6951503 (Open Web Text)

Max Activating Token Index: 964

Text #15

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.3472. Min Act: -0.1700

Data Index: 8548381 (Open Web Text)

Max Activating Token Index: 682

Text #16

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.3320. Min Act: -0.1700

Data Index: 1221793 (Open Web Text)

Max Activating Token Index: 885

Text #17

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.3434. Min Act: -0.1700

Data Index: 1949107 (Open Web Text)

Max Activating Token Index: 767

Text #18

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.3169. Min Act: -0.1700

Data Index: 157745 (Open Web Text)

Max Activating Token Index: 761

Text #19

Max Range: 4.7424. Min Range: -4.7424

Max Act: 4.3623. Min Act: -0.1700

Data Index: 3906185 (Open Web Text)

Max Activating Token Index: 479