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

Dataset: Open Web Text

Neuron 1819 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: 5.0468. Min Range: -5.0468

Max Act: 5.0468. Min Act: -0.1700

Data Index: 3745884 (Open Web Text)

Max Activating Token Index: 603

Text #1

Max Range: 5.0468. Min Range: -5.0468

Max Act: 5.0365. Min Act: -0.1700

Data Index: 2494900 (Open Web Text)

Max Activating Token Index: 968

Text #2

Max Range: 5.0468. Min Range: -5.0468

Max Act: 5.0400. Min Act: -0.1700

Data Index: 3195507 (Open Web Text)

Max Activating Token Index: 361

Text #3

Max Range: 5.0468. Min Range: -5.0468

Max Act: 5.0312. Min Act: -0.1700

Data Index: 5282518 (Open Web Text)

Max Activating Token Index: 656

Text #4

Max Range: 5.0468. Min Range: -5.0468

Max Act: 4.9981. Min Act: -0.1700

Data Index: 4178479 (Open Web Text)

Max Activating Token Index: 897

Text #5

Max Range: 5.0468. Min Range: -5.0468

Max Act: 5.0137. Min Act: -0.1700

Data Index: 2579291 (Open Web Text)

Max Activating Token Index: 593

Text #6

Max Range: 5.0468. Min Range: -5.0468

Max Act: 4.9674. Min Act: -0.1700

Data Index: 4352467 (Open Web Text)

Max Activating Token Index: 361

Text #7

Max Range: 5.0468. Min Range: -5.0468

Max Act: 4.9331. Min Act: -0.1700

Data Index: 6414042 (Open Web Text)

Max Activating Token Index: 101

Text #8

Max Range: 5.0468. Min Range: -5.0468

Max Act: 4.9181. Min Act: -0.1700

Data Index: 2255195 (Open Web Text)

Max Activating Token Index: 68

Text #9

Max Range: 5.0468. Min Range: -5.0468

Max Act: 4.8927. Min Act: -0.1700

Data Index: 2192536 (Open Web Text)

Max Activating Token Index: 644

Text #10

Max Range: 5.0468. Min Range: -5.0468

Max Act: 4.9345. Min Act: -0.1700

Data Index: 7516524 (Open Web Text)

Max Activating Token Index: 899

Text #11

Max Range: 5.0468. Min Range: -5.0468

Max Act: 4.8942. Min Act: -0.1700

Data Index: 8473226 (Open Web Text)

Max Activating Token Index: 910

Text #12

Max Range: 5.0468. Min Range: -5.0468

Max Act: 4.8771. Min Act: -0.1700

Data Index: 4635084 (Open Web Text)

Max Activating Token Index: 540

Text #13

Max Range: 5.0468. Min Range: -5.0468

Max Act: 4.8577. Min Act: -0.1700

Data Index: 6208645 (Open Web Text)

Max Activating Token Index: 460

Text #14

Max Range: 5.0468. Min Range: -5.0468

Max Act: 4.8825. Min Act: -0.1700

Data Index: 7746299 (Open Web Text)

Max Activating Token Index: 104

Text #15

Max Range: 5.0468. Min Range: -5.0468

Max Act: 4.9029. Min Act: -0.1700

Data Index: 2918552 (Open Web Text)

Max Activating Token Index: 726

Text #16

Max Range: 5.0468. Min Range: -5.0468

Max Act: 4.8129. Min Act: -0.1700

Data Index: 437995 (Open Web Text)

Max Activating Token Index: 144

Text #17

Max Range: 5.0468. Min Range: -5.0468

Max Act: 4.8261. Min Act: -0.1700

Data Index: 2160411 (Open Web Text)

Max Activating Token Index: 539

Text #18

Max Range: 5.0468. Min Range: -5.0468

Max Act: 4.8139. Min Act: -0.1700

Data Index: 4583117 (Open Web Text)

Max Activating Token Index: 251

Text #19

Max Range: 5.0468. Min Range: -5.0468

Max Act: 4.8380. Min Act: -0.1700

Data Index: 3753502 (Open Web Text)

Max Activating Token Index: 819