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

Dataset: Open Web Text

Neuron 2946 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: 1.5602. Min Range: -1.5602

Max Act: 1.5602. Min Act: -0.1700

Data Index: 751693 (Open Web Text)

Max Activating Token Index: 203

Text #1

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.5515. Min Act: -0.1700

Data Index: 3730552 (Open Web Text)

Max Activating Token Index: 665

Text #2

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.5442. Min Act: -0.1700

Data Index: 8404035 (Open Web Text)

Max Activating Token Index: 344

Text #3

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.5160. Min Act: -0.1698

Data Index: 4323084 (Open Web Text)

Max Activating Token Index: 628

Text #4

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.5183. Min Act: -0.1700

Data Index: 7441178 (Open Web Text)

Max Activating Token Index: 261

Text #5

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.5184. Min Act: -0.1700

Data Index: 6308260 (Open Web Text)

Max Activating Token Index: 174

Text #6

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.5113. Min Act: -0.1700

Data Index: 4291225 (Open Web Text)

Max Activating Token Index: 602

Text #7

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.5184. Min Act: -0.1700

Data Index: 5593557 (Open Web Text)

Max Activating Token Index: 318

Text #8

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.5232. Min Act: -0.1699

Data Index: 6329044 (Open Web Text)

Max Activating Token Index: 256

Text #9

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.5109. Min Act: -0.1698

Data Index: 1319201 (Open Web Text)

Max Activating Token Index: 131

Text #10

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.5069. Min Act: -0.1700

Data Index: 6532317 (Open Web Text)

Max Activating Token Index: 653

Text #11

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.5140. Min Act: -0.1698

Data Index: 6050089 (Open Web Text)

Max Activating Token Index: 122

Text #12

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.5106. Min Act: -0.1700

Data Index: 6887411 (Open Web Text)

Max Activating Token Index: 362

Text #13

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.5102. Min Act: -0.1700

Data Index: 6609201 (Open Web Text)

Max Activating Token Index: 222

Text #14

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.5018. Min Act: -0.1700

Data Index: 1303636 (Open Web Text)

Max Activating Token Index: 12

Text #15

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.5020. Min Act: -0.1690

Data Index: 5234186 (Open Web Text)

Max Activating Token Index: 226

Text #16

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.4918. Min Act: -0.1700

Data Index: 8536743 (Open Web Text)

Max Activating Token Index: 297

Text #17

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.4962. Min Act: -0.1700

Data Index: 5664969 (Open Web Text)

Max Activating Token Index: 155

Text #18

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.5050. Min Act: -0.1700

Data Index: 194914 (Open Web Text)

Max Activating Token Index: 656

Text #19

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.4866. Min Act: -0.1700

Data Index: 141686 (Open Web Text)

Max Activating Token Index: 158