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

Dataset: Open Web Text

Neuron 3021 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: 4.0908. Min Range: -4.0908

Max Act: 4.0908. Min Act: -0.1700

Data Index: 6248207 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 4.0908. Min Range: -4.0908

Max Act: 4.0496. Min Act: -0.1700

Data Index: 4282336 (Open Web Text)

Max Activating Token Index: 397

Text #2

Max Range: 4.0908. Min Range: -4.0908

Max Act: 3.9759. Min Act: -0.1700

Data Index: 4997353 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 4.0908. Min Range: -4.0908

Max Act: 3.9977. Min Act: -0.1700

Data Index: 3523951 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.0908. Min Range: -4.0908

Max Act: 3.9759. Min Act: -0.1700

Data Index: 8720992 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 4.0908. Min Range: -4.0908

Max Act: 3.9759. Min Act: -0.1700

Data Index: 1034331 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 4.0908. Min Range: -4.0908

Max Act: 3.9759. Min Act: -0.1700

Data Index: 5675489 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 4.0908. Min Range: -4.0908

Max Act: 3.9315. Min Act: -0.1700

Data Index: 1097040 (Open Web Text)

Max Activating Token Index: 285

Text #8

Max Range: 4.0908. Min Range: -4.0908

Max Act: 3.9403. Min Act: -0.1700

Data Index: 8303028 (Open Web Text)

Max Activating Token Index: 415

Text #9

Max Range: 4.0908. Min Range: -4.0908

Max Act: 3.9835. Min Act: -0.1700

Data Index: 4816923 (Open Web Text)

Max Activating Token Index: 36

Text #10

Max Range: 4.0908. Min Range: -4.0908

Max Act: 3.9420. Min Act: -0.1700

Data Index: 4888942 (Open Web Text)

Max Activating Token Index: 40

Text #11

Max Range: 4.0908. Min Range: -4.0908

Max Act: 3.9159. Min Act: -0.1700

Data Index: 6477499 (Open Web Text)

Max Activating Token Index: 575

Text #12

Max Range: 4.0908. Min Range: -4.0908

Max Act: 3.9142. Min Act: -0.1700

Data Index: 1790437 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 4.0908. Min Range: -4.0908

Max Act: 3.9190. Min Act: -0.1700

Data Index: 7187856 (Open Web Text)

Max Activating Token Index: 161

Text #14

Max Range: 4.0908. Min Range: -4.0908

Max Act: 3.9142. Min Act: -0.1700

Data Index: 2957417 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 4.0908. Min Range: -4.0908

Max Act: 3.8805. Min Act: -0.1700

Data Index: 7970479 (Open Web Text)

Max Activating Token Index: 18

Text #16

Max Range: 4.0908. Min Range: -4.0908

Max Act: 3.8597. Min Act: -0.1700

Data Index: 6948063 (Open Web Text)

Max Activating Token Index: 448

Text #17

Max Range: 4.0908. Min Range: -4.0908

Max Act: 3.8430. Min Act: -0.1700

Data Index: 7598223 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 4.0908. Min Range: -4.0908

Max Act: 3.8647. Min Act: -0.1700

Data Index: 5472035 (Open Web Text)

Max Activating Token Index: 68

Text #19

Max Range: 4.0908. Min Range: -4.0908

Max Act: 3.8434. Min Act: -0.1700

Data Index: 3004450 (Open Web Text)

Max Activating Token Index: 278