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

Dataset: Open Web Text

Neuron 1397 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: 3.1159. Min Range: -3.1159

Max Act: 3.1159. Min Act: -0.1700

Data Index: 2521212 (Open Web Text)

Max Activating Token Index: 748

Text #1

Max Range: 3.1159. Min Range: -3.1159

Max Act: 3.1096. Min Act: -0.1700

Data Index: 3323550 (Open Web Text)

Max Activating Token Index: 489

Text #2

Max Range: 3.1159. Min Range: -3.1159

Max Act: 3.0480. Min Act: -0.1700

Data Index: 3091971 (Open Web Text)

Max Activating Token Index: 713

Text #3

Max Range: 3.1159. Min Range: -3.1159

Max Act: 3.0176. Min Act: -0.1700

Data Index: 2616286 (Open Web Text)

Max Activating Token Index: 88

Text #4

Max Range: 3.1159. Min Range: -3.1159

Max Act: 3.0043. Min Act: -0.1700

Data Index: 2839810 (Open Web Text)

Max Activating Token Index: 459

Text #5

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.9613. Min Act: -0.1700

Data Index: 560997 (Open Web Text)

Max Activating Token Index: 288

Text #6

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.9784. Min Act: -0.1700

Data Index: 2428794 (Open Web Text)

Max Activating Token Index: 827

Text #7

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.9749. Min Act: -0.1700

Data Index: 6420577 (Open Web Text)

Max Activating Token Index: 432

Text #8

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.9545. Min Act: -0.1700

Data Index: 4354179 (Open Web Text)

Max Activating Token Index: 847

Text #9

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.9480. Min Act: -0.1700

Data Index: 8431024 (Open Web Text)

Max Activating Token Index: 193

Text #10

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.9339. Min Act: -0.1700

Data Index: 6473719 (Open Web Text)

Max Activating Token Index: 369

Text #11

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.9294. Min Act: -0.1700

Data Index: 6084797 (Open Web Text)

Max Activating Token Index: 944

Text #12

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.9373. Min Act: -0.1700

Data Index: 141253 (Open Web Text)

Max Activating Token Index: 833

Text #13

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.9304. Min Act: -0.1700

Data Index: 6933450 (Open Web Text)

Max Activating Token Index: 304

Text #14

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.9430. Min Act: -0.1700

Data Index: 3155199 (Open Web Text)

Max Activating Token Index: 884

Text #15

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.9042. Min Act: -0.1700

Data Index: 2161300 (Open Web Text)

Max Activating Token Index: 1011

Text #16

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.8908. Min Act: -0.1700

Data Index: 6064584 (Open Web Text)

Max Activating Token Index: 570

Text #17

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.8939. Min Act: -0.1700

Data Index: 5515961 (Open Web Text)

Max Activating Token Index: 446

Text #18

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.9003. Min Act: -0.1700

Data Index: 6784886 (Open Web Text)

Max Activating Token Index: 456

Text #19

Max Range: 3.1159. Min Range: -3.1159

Max Act: 2.8807. Min Act: -0.1700

Data Index: 6552720 (Open Web Text)

Max Activating Token Index: 558