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

Dataset: Open Web Text

Neuron 3055 in Layer 5

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: 5.3969. Min Range: -5.3969

Max Act: 5.3969. Min Act: -0.1700

Data Index: 3877808 (Open Web Text)

Max Activating Token Index: 304

Text #1

Max Range: 5.3969. Min Range: -5.3969

Max Act: 5.1498. Min Act: -0.1700

Data Index: 1710251 (Open Web Text)

Max Activating Token Index: 783

Text #2

Max Range: 5.3969. Min Range: -5.3969

Max Act: 5.0512. Min Act: -0.1700

Data Index: 2634244 (Open Web Text)

Max Activating Token Index: 145

Text #3

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.9912. Min Act: -0.1700

Data Index: 5677050 (Open Web Text)

Max Activating Token Index: 173

Text #4

Max Range: 5.3969. Min Range: -5.3969

Max Act: 5.0301. Min Act: -0.1700

Data Index: 3163512 (Open Web Text)

Max Activating Token Index: 687

Text #5

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.9893. Min Act: -0.1700

Data Index: 972647 (Open Web Text)

Max Activating Token Index: 575

Text #6

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.9815. Min Act: -0.1700

Data Index: 5155899 (Open Web Text)

Max Activating Token Index: 469

Text #7

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.9012. Min Act: -0.1700

Data Index: 7169730 (Open Web Text)

Max Activating Token Index: 84

Text #8

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.9271. Min Act: -0.1700

Data Index: 4671430 (Open Web Text)

Max Activating Token Index: 687

Text #9

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.8932. Min Act: -0.1700

Data Index: 1158345 (Open Web Text)

Max Activating Token Index: 782

Text #10

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.9028. Min Act: -0.1700

Data Index: 7304454 (Open Web Text)

Max Activating Token Index: 728

Text #11

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.8795. Min Act: -0.1700

Data Index: 2933313 (Open Web Text)

Max Activating Token Index: 701

Text #12

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.9029. Min Act: -0.1700

Data Index: 238615 (Open Web Text)

Max Activating Token Index: 368

Text #13

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.8842. Min Act: -0.1700

Data Index: 6754568 (Open Web Text)

Max Activating Token Index: 579

Text #14

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.8791. Min Act: -0.1700

Data Index: 3402501 (Open Web Text)

Max Activating Token Index: 898

Text #15

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.8974. Min Act: -0.1700

Data Index: 3929970 (Open Web Text)

Max Activating Token Index: 424

Text #16

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.8750. Min Act: -0.1700

Data Index: 3120540 (Open Web Text)

Max Activating Token Index: 513

Text #17

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.8610. Min Act: -0.1700

Data Index: 7059996 (Open Web Text)

Max Activating Token Index: 419

Text #18

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.8727. Min Act: -0.1700

Data Index: 6455243 (Open Web Text)

Max Activating Token Index: 113

Text #19

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.8360. Min Act: -0.1700

Data Index: 468158 (Open Web Text)

Max Activating Token Index: 477