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

Dataset: Open Web Text

Neuron 700 in Layer 2

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: 4.6100. Min Range: -4.6100

Max Act: 4.6100. Min Act: -0.1700

Data Index: 7614545 (Open Web Text)

Max Activating Token Index: 269

Text #1

Max Range: 4.6100. Min Range: -4.6100

Max Act: 4.5389. Min Act: -0.1700

Data Index: 5042836 (Open Web Text)

Max Activating Token Index: 481

Text #2

Max Range: 4.6100. Min Range: -4.6100

Max Act: 4.4980. Min Act: -0.1700

Data Index: 6180130 (Open Web Text)

Max Activating Token Index: 35

Text #3

Max Range: 4.6100. Min Range: -4.6100

Max Act: 4.4206. Min Act: -0.1700

Data Index: 7662332 (Open Web Text)

Max Activating Token Index: 174

Text #4

Max Range: 4.6100. Min Range: -4.6100

Max Act: 4.4362. Min Act: -0.1700

Data Index: 8444299 (Open Web Text)

Max Activating Token Index: 458

Text #5

Max Range: 4.6100. Min Range: -4.6100

Max Act: 4.3791. Min Act: -0.1700

Data Index: 8597029 (Open Web Text)

Max Activating Token Index: 579

Text #6

Max Range: 4.6100. Min Range: -4.6100

Max Act: 4.3640. Min Act: -0.1700

Data Index: 5833192 (Open Web Text)

Max Activating Token Index: 976

Text #7

Max Range: 4.6100. Min Range: -4.6100

Max Act: 4.3764. Min Act: -0.1700

Data Index: 6092775 (Open Web Text)

Max Activating Token Index: 783

Text #8

Max Range: 4.6100. Min Range: -4.6100

Max Act: 4.3153. Min Act: -0.1700

Data Index: 8405169 (Open Web Text)

Max Activating Token Index: 29

Text #9

Max Range: 4.6100. Min Range: -4.6100

Max Act: 4.3067. Min Act: -0.1700

Data Index: 3530484 (Open Web Text)

Max Activating Token Index: 59

Text #10

Max Range: 4.6100. Min Range: -4.6100

Max Act: 4.3215. Min Act: -0.1700

Data Index: 8450640 (Open Web Text)

Max Activating Token Index: 632

Text #11

Max Range: 4.6100. Min Range: -4.6100

Max Act: 4.3311. Min Act: -0.1700

Data Index: 6826024 (Open Web Text)

Max Activating Token Index: 515

Text #12

Max Range: 4.6100. Min Range: -4.6100

Max Act: 4.2500. Min Act: -0.1700

Data Index: 2808035 (Open Web Text)

Max Activating Token Index: 942

Text #13

Max Range: 4.6100. Min Range: -4.6100

Max Act: 4.2461. Min Act: -0.1700

Data Index: 6213176 (Open Web Text)

Max Activating Token Index: 442

Text #14

Max Range: 4.6100. Min Range: -4.6100

Max Act: 4.2402. Min Act: -0.1700

Data Index: 8450638 (Open Web Text)

Max Activating Token Index: 251

Text #15

Max Range: 4.6100. Min Range: -4.6100

Max Act: 4.2018. Min Act: -0.1700

Data Index: 3460343 (Open Web Text)

Max Activating Token Index: 25

Text #16

Max Range: 4.6100. Min Range: -4.6100

Max Act: 4.1782. Min Act: -0.1700

Data Index: 3142236 (Open Web Text)

Max Activating Token Index: 147

Text #17

Max Range: 4.6100. Min Range: -4.6100

Max Act: 4.2057. Min Act: -0.1700

Data Index: 631165 (Open Web Text)

Max Activating Token Index: 15

Text #18

Max Range: 4.6100. Min Range: -4.6100

Max Act: 4.2065. Min Act: -0.1700

Data Index: 7631044 (Open Web Text)

Max Activating Token Index: 955

Text #19

Max Range: 4.6100. Min Range: -4.6100

Max Act: 4.2360. Min Act: -0.1700

Data Index: 2064177 (Open Web Text)

Max Activating Token Index: 503