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

Dataset: Open Web Text

Neuron 54 in Layer 3

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: 4.0466. Min Range: -4.0466

Max Act: 4.0466. Min Act: -0.1700

Data Index: 2127205 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.0466. Min Range: -4.0466

Max Act: 4.0092. Min Act: -0.1700

Data Index: 1023142 (Open Web Text)

Max Activating Token Index: 157

Text #2

Max Range: 4.0466. Min Range: -4.0466

Max Act: 4.0124. Min Act: -0.1700

Data Index: 5893508 (Open Web Text)

Max Activating Token Index: 323

Text #3

Max Range: 4.0466. Min Range: -4.0466

Max Act: 3.9756. Min Act: -0.1700

Data Index: 393758 (Open Web Text)

Max Activating Token Index: 476

Text #4

Max Range: 4.0466. Min Range: -4.0466

Max Act: 3.9505. Min Act: -0.1700

Data Index: 7124289 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.0466. Min Range: -4.0466

Max Act: 3.9516. Min Act: -0.1700

Data Index: 3444464 (Open Web Text)

Max Activating Token Index: 253

Text #6

Max Range: 4.0466. Min Range: -4.0466

Max Act: 3.9302. Min Act: -0.1700

Data Index: 363736 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.0466. Min Range: -4.0466

Max Act: 3.9333. Min Act: -0.1700

Data Index: 6692522 (Open Web Text)

Max Activating Token Index: 111

Text #8

Max Range: 4.0466. Min Range: -4.0466

Max Act: 3.9302. Min Act: -0.1700

Data Index: 1668181 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 4.0466. Min Range: -4.0466

Max Act: 3.9302. Min Act: -0.1700

Data Index: 2968462 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.0466. Min Range: -4.0466

Max Act: 3.9203. Min Act: -0.1700

Data Index: 5623255 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 4.0466. Min Range: -4.0466

Max Act: 3.9302. Min Act: -0.1700

Data Index: 5446800 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.0466. Min Range: -4.0466

Max Act: 3.9302. Min Act: -0.1700

Data Index: 2527724 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.0466. Min Range: -4.0466

Max Act: 3.9336. Min Act: -0.1700

Data Index: 1637552 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.0466. Min Range: -4.0466

Max Act: 3.9302. Min Act: -0.1700

Data Index: 578980 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 4.0466. Min Range: -4.0466

Max Act: 3.9302. Min Act: -0.1700

Data Index: 4702390 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 4.0466. Min Range: -4.0466

Max Act: 3.9173. Min Act: -0.1700

Data Index: 3902323 (Open Web Text)

Max Activating Token Index: 415

Text #17

Max Range: 4.0466. Min Range: -4.0466

Max Act: 3.9302. Min Act: -0.1700

Data Index: 3549087 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.0466. Min Range: -4.0466

Max Act: 3.9014. Min Act: -0.1700

Data Index: 1467169 (Open Web Text)

Max Activating Token Index: 187

Text #19

Max Range: 4.0466. Min Range: -4.0466

Max Act: 3.9302. Min Act: -0.1700

Data Index: 3179217 (Open Web Text)

Max Activating Token Index: 6