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

Dataset: Open Web Text

Neuron 1413 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: 3.7898. Min Range: -3.7898

Max Act: 3.7898. Min Act: -0.1700

Data Index: 418297 (Open Web Text)

Max Activating Token Index: 457

Text #1

Max Range: 3.7898. Min Range: -3.7898

Max Act: 3.6992. Min Act: -0.1700

Data Index: 5689175 (Open Web Text)

Max Activating Token Index: 874

Text #2

Max Range: 3.7898. Min Range: -3.7898

Max Act: 3.6304. Min Act: -0.1700

Data Index: 4106501 (Open Web Text)

Max Activating Token Index: 194

Text #3

Max Range: 3.7898. Min Range: -3.7898

Max Act: 3.5955. Min Act: -0.1700

Data Index: 4226577 (Open Web Text)

Max Activating Token Index: 750

Text #4

Max Range: 3.7898. Min Range: -3.7898

Max Act: 3.6199. Min Act: -0.1700

Data Index: 5689174 (Open Web Text)

Max Activating Token Index: 61

Text #5

Max Range: 3.7898. Min Range: -3.7898

Max Act: 3.6135. Min Act: -0.1700

Data Index: 4068895 (Open Web Text)

Max Activating Token Index: 466

Text #6

Max Range: 3.7898. Min Range: -3.7898

Max Act: 3.6127. Min Act: -0.1700

Data Index: 195282 (Open Web Text)

Max Activating Token Index: 266

Text #7

Max Range: 3.7898. Min Range: -3.7898

Max Act: 3.5952. Min Act: -0.1700

Data Index: 5925435 (Open Web Text)

Max Activating Token Index: 210

Text #8

Max Range: 3.7898. Min Range: -3.7898

Max Act: 3.6024. Min Act: -0.1700

Data Index: 731365 (Open Web Text)

Max Activating Token Index: 170

Text #9

Max Range: 3.7898. Min Range: -3.7898

Max Act: 3.5869. Min Act: -0.1700

Data Index: 2772020 (Open Web Text)

Max Activating Token Index: 676

Text #10

Max Range: 3.7898. Min Range: -3.7898

Max Act: 3.5609. Min Act: -0.1700

Data Index: 114696 (Open Web Text)

Max Activating Token Index: 498

Text #11

Max Range: 3.7898. Min Range: -3.7898

Max Act: 3.5452. Min Act: -0.1700

Data Index: 7106837 (Open Web Text)

Max Activating Token Index: 760

Text #12

Max Range: 3.7898. Min Range: -3.7898

Max Act: 3.5658. Min Act: -0.1700

Data Index: 3225630 (Open Web Text)

Max Activating Token Index: 357

Text #13

Max Range: 3.7898. Min Range: -3.7898

Max Act: 3.5742. Min Act: -0.1700

Data Index: 6411380 (Open Web Text)

Max Activating Token Index: 296

Text #14

Max Range: 3.7898. Min Range: -3.7898

Max Act: 3.4535. Min Act: -0.1700

Data Index: 2378392 (Open Web Text)

Max Activating Token Index: 1020

Text #15

Max Range: 3.7898. Min Range: -3.7898

Max Act: 3.5310. Min Act: -0.1700

Data Index: 6206090 (Open Web Text)

Max Activating Token Index: 965

Text #16

Max Range: 3.7898. Min Range: -3.7898

Max Act: 3.5309. Min Act: -0.1700

Data Index: 8372751 (Open Web Text)

Max Activating Token Index: 630

Text #17

Max Range: 3.7898. Min Range: -3.7898

Max Act: 3.5010. Min Act: -0.1700

Data Index: 6970146 (Open Web Text)

Max Activating Token Index: 567

Text #18

Max Range: 3.7898. Min Range: -3.7898

Max Act: 3.5120. Min Act: -0.1700

Data Index: 4834052 (Open Web Text)

Max Activating Token Index: 943

Text #19

Max Range: 3.7898. Min Range: -3.7898

Max Act: 3.4734. Min Act: -0.1700

Data Index: 3248253 (Open Web Text)

Max Activating Token Index: 116