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

Dataset: Open Web Text

Neuron 279 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: 3.6985. Min Range: -3.6985

Max Act: 3.6985. Min Act: -0.1700

Data Index: 2897364 (Open Web Text)

Max Activating Token Index: 1009

Text #1

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.5901. Min Act: -0.1700

Data Index: 8566352 (Open Web Text)

Max Activating Token Index: 195

Text #2

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.5974. Min Act: -0.1700

Data Index: 1985089 (Open Web Text)

Max Activating Token Index: 212

Text #3

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.5525. Min Act: -0.1700

Data Index: 7751647 (Open Web Text)

Max Activating Token Index: 376

Text #4

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.6009. Min Act: -0.1700

Data Index: 3723392 (Open Web Text)

Max Activating Token Index: 290

Text #5

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.5503. Min Act: -0.1700

Data Index: 7162131 (Open Web Text)

Max Activating Token Index: 523

Text #6

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.5217. Min Act: -0.1700

Data Index: 1969134 (Open Web Text)

Max Activating Token Index: 314

Text #7

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.5282. Min Act: -0.1700

Data Index: 3607044 (Open Web Text)

Max Activating Token Index: 496

Text #8

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.5206. Min Act: -0.1700

Data Index: 6199947 (Open Web Text)

Max Activating Token Index: 888

Text #9

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.5063. Min Act: -0.1700

Data Index: 7729735 (Open Web Text)

Max Activating Token Index: 269

Text #10

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.4828. Min Act: -0.1700

Data Index: 7665524 (Open Web Text)

Max Activating Token Index: 845

Text #11

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.5283. Min Act: -0.1700

Data Index: 68603 (Open Web Text)

Max Activating Token Index: 329

Text #12

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.4673. Min Act: -0.1700

Data Index: 4377225 (Open Web Text)

Max Activating Token Index: 77

Text #13

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.4884. Min Act: -0.1700

Data Index: 2169370 (Open Web Text)

Max Activating Token Index: 998

Text #14

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.5058. Min Act: -0.1700

Data Index: 3004905 (Open Web Text)

Max Activating Token Index: 527

Text #15

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.4739. Min Act: -0.1700

Data Index: 654703 (Open Web Text)

Max Activating Token Index: 240

Text #16

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.4878. Min Act: -0.1700

Data Index: 1369023 (Open Web Text)

Max Activating Token Index: 502

Text #17

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.4587. Min Act: -0.1700

Data Index: 1810068 (Open Web Text)

Max Activating Token Index: 247

Text #18

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.4744. Min Act: -0.1700

Data Index: 1164293 (Open Web Text)

Max Activating Token Index: 382

Text #19

Max Range: 3.6985. Min Range: -3.6985

Max Act: 3.4360. Min Act: -0.1700

Data Index: 7262733 (Open Web Text)

Max Activating Token Index: 497