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

Dataset: Open Web Text

Neuron 2375 in Layer 6

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: 3.7032. Min Range: -3.7032

Max Act: 3.7032. Min Act: -0.1700

Data Index: 7486176 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.6655. Min Act: -0.1700

Data Index: 4918015 (Open Web Text)

Max Activating Token Index: 674

Text #2

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.5734. Min Act: -0.1700

Data Index: 3164376 (Open Web Text)

Max Activating Token Index: 359

Text #3

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.5948. Min Act: -0.1700

Data Index: 2508057 (Open Web Text)

Max Activating Token Index: 213

Text #4

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.5632. Min Act: -0.1700

Data Index: 7287700 (Open Web Text)

Max Activating Token Index: 653

Text #5

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.5404. Min Act: -0.1700

Data Index: 1178295 (Open Web Text)

Max Activating Token Index: 636

Text #6

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.5522. Min Act: -0.1700

Data Index: 1856056 (Open Web Text)

Max Activating Token Index: 620

Text #7

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.5082. Min Act: -0.1700

Data Index: 4055518 (Open Web Text)

Max Activating Token Index: 551

Text #8

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.5250. Min Act: -0.1700

Data Index: 3483436 (Open Web Text)

Max Activating Token Index: 86

Text #9

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.4936. Min Act: -0.1700

Data Index: 853049 (Open Web Text)

Max Activating Token Index: 455

Text #10

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.4805. Min Act: -0.1700

Data Index: 7718431 (Open Web Text)

Max Activating Token Index: 927

Text #11

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.4962. Min Act: -0.1700

Data Index: 200294 (Open Web Text)

Max Activating Token Index: 344

Text #12

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.4950. Min Act: -0.1700

Data Index: 6145698 (Open Web Text)

Max Activating Token Index: 29

Text #13

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.4852. Min Act: -0.1700

Data Index: 3718316 (Open Web Text)

Max Activating Token Index: 98

Text #14

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.4838. Min Act: -0.1700

Data Index: 5652982 (Open Web Text)

Max Activating Token Index: 412

Text #15

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.4630. Min Act: -0.1700

Data Index: 3164374 (Open Web Text)

Max Activating Token Index: 316

Text #16

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.4819. Min Act: -0.1700

Data Index: 6838572 (Open Web Text)

Max Activating Token Index: 726

Text #17

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.4749. Min Act: -0.1700

Data Index: 3308832 (Open Web Text)

Max Activating Token Index: 173

Text #18

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.4772. Min Act: -0.1700

Data Index: 877844 (Open Web Text)

Max Activating Token Index: 68

Text #19

Max Range: 3.7032. Min Range: -3.7032

Max Act: 3.4470. Min Act: -0.1700

Data Index: 6191621 (Open Web Text)

Max Activating Token Index: 495