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

Dataset: Open Web Text

Neuron 1462 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: 3.3943. Min Range: -3.3943

Max Act: 3.3943. Min Act: -0.1700

Data Index: 1961784 (Open Web Text)

Max Activating Token Index: 743

Text #1

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.3797. Min Act: -0.1700

Data Index: 2538255 (Open Web Text)

Max Activating Token Index: 839

Text #2

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.3878. Min Act: -0.1700

Data Index: 6619537 (Open Web Text)

Max Activating Token Index: 102

Text #3

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.2242. Min Act: -0.1700

Data Index: 6771777 (Open Web Text)

Max Activating Token Index: 61

Text #4

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.0856. Min Act: -0.1700

Data Index: 8254069 (Open Web Text)

Max Activating Token Index: 142

Text #5

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.0732. Min Act: -0.1700

Data Index: 1235509 (Open Web Text)

Max Activating Token Index: 80

Text #6

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.0752. Min Act: -0.1700

Data Index: 7083390 (Open Web Text)

Max Activating Token Index: 201

Text #7

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.0516. Min Act: -0.1700

Data Index: 3853333 (Open Web Text)

Max Activating Token Index: 33

Text #8

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.0461. Min Act: -0.1700

Data Index: 6642833 (Open Web Text)

Max Activating Token Index: 665

Text #9

Max Range: 3.3943. Min Range: -3.3943

Max Act: 3.0260. Min Act: -0.1700

Data Index: 8210147 (Open Web Text)

Max Activating Token Index: 608

Text #10

Max Range: 3.3943. Min Range: -3.3943

Max Act: 2.9849. Min Act: -0.1700

Data Index: 459935 (Open Web Text)

Max Activating Token Index: 176

Text #11

Max Range: 3.3943. Min Range: -3.3943

Max Act: 2.9884. Min Act: -0.1700

Data Index: 253090 (Open Web Text)

Max Activating Token Index: 148

Text #12

Max Range: 3.3943. Min Range: -3.3943

Max Act: 2.9605. Min Act: -0.1700

Data Index: 155962 (Open Web Text)

Max Activating Token Index: 564

Text #13

Max Range: 3.3943. Min Range: -3.3943

Max Act: 2.9366. Min Act: -0.1700

Data Index: 4193459 (Open Web Text)

Max Activating Token Index: 35

Text #14

Max Range: 3.3943. Min Range: -3.3943

Max Act: 2.9366. Min Act: -0.1700

Data Index: 6208681 (Open Web Text)

Max Activating Token Index: 30

Text #15

Max Range: 3.3943. Min Range: -3.3943

Max Act: 2.9209. Min Act: -0.1700

Data Index: 4216939 (Open Web Text)

Max Activating Token Index: 426

Text #16

Max Range: 3.3943. Min Range: -3.3943

Max Act: 2.9214. Min Act: -0.1700

Data Index: 5485694 (Open Web Text)

Max Activating Token Index: 287

Text #17

Max Range: 3.3943. Min Range: -3.3943

Max Act: 2.9203. Min Act: -0.1700

Data Index: 6617483 (Open Web Text)

Max Activating Token Index: 521

Text #18

Max Range: 3.3943. Min Range: -3.3943

Max Act: 2.9123. Min Act: -0.1700

Data Index: 4951803 (Open Web Text)

Max Activating Token Index: 350

Text #19

Max Range: 3.3943. Min Range: -3.3943

Max Act: 2.9041. Min Act: -0.1700

Data Index: 7828817 (Open Web Text)

Max Activating Token Index: 637