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

Dataset: Open Web Text

Neuron 842 in Layer 1

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: 3.2262. Min Range: -3.2262

Max Act: 3.2262. Min Act: -0.1700

Data Index: 2148048 (Open Web Text)

Max Activating Token Index: 231

Text #1

Max Range: 3.2262. Min Range: -3.2262

Max Act: 3.0518. Min Act: -0.1700

Data Index: 1554272 (Open Web Text)

Max Activating Token Index: 580

Text #2

Max Range: 3.2262. Min Range: -3.2262

Max Act: 2.9996. Min Act: -0.1700

Data Index: 4127053 (Open Web Text)

Max Activating Token Index: 595

Text #3

Max Range: 3.2262. Min Range: -3.2262

Max Act: 2.9641. Min Act: -0.1700

Data Index: 3862324 (Open Web Text)

Max Activating Token Index: 101

Text #4

Max Range: 3.2262. Min Range: -3.2262

Max Act: 2.9734. Min Act: -0.1700

Data Index: 3849874 (Open Web Text)

Max Activating Token Index: 125

Text #5

Max Range: 3.2262. Min Range: -3.2262

Max Act: 2.9550. Min Act: -0.1700

Data Index: 5065284 (Open Web Text)

Max Activating Token Index: 330

Text #6

Max Range: 3.2262. Min Range: -3.2262

Max Act: 2.9709. Min Act: -0.1700

Data Index: 8207201 (Open Web Text)

Max Activating Token Index: 101

Text #7

Max Range: 3.2262. Min Range: -3.2262

Max Act: 2.9555. Min Act: -0.1700

Data Index: 7455022 (Open Web Text)

Max Activating Token Index: 159

Text #8

Max Range: 3.2262. Min Range: -3.2262

Max Act: 2.9488. Min Act: -0.1698

Data Index: 1142953 (Open Web Text)

Max Activating Token Index: 95

Text #9

Max Range: 3.2262. Min Range: -3.2262

Max Act: 2.9343. Min Act: -0.1700

Data Index: 3730146 (Open Web Text)

Max Activating Token Index: 107

Text #10

Max Range: 3.2262. Min Range: -3.2262

Max Act: 2.9527. Min Act: -0.1700

Data Index: 3754370 (Open Web Text)

Max Activating Token Index: 227

Text #11

Max Range: 3.2262. Min Range: -3.2262

Max Act: 2.9511. Min Act: -0.1700

Data Index: 3783230 (Open Web Text)

Max Activating Token Index: 158

Text #12

Max Range: 3.2262. Min Range: -3.2262

Max Act: 2.9210. Min Act: -0.1700

Data Index: 12951 (Open Web Text)

Max Activating Token Index: 79

Text #13

Max Range: 3.2262. Min Range: -3.2262

Max Act: 2.9270. Min Act: -0.1700

Data Index: 2652431 (Open Web Text)

Max Activating Token Index: 33

Text #14

Max Range: 3.2262. Min Range: -3.2262

Max Act: 2.9295. Min Act: -0.1700

Data Index: 2313475 (Open Web Text)

Max Activating Token Index: 301

Text #15

Max Range: 3.2262. Min Range: -3.2262

Max Act: 2.9139. Min Act: -0.1700

Data Index: 1570753 (Open Web Text)

Max Activating Token Index: 160

Text #16

Max Range: 3.2262. Min Range: -3.2262

Max Act: 2.9153. Min Act: -0.1700

Data Index: 7349153 (Open Web Text)

Max Activating Token Index: 103

Text #17

Max Range: 3.2262. Min Range: -3.2262

Max Act: 2.9231. Min Act: -0.1700

Data Index: 7503623 (Open Web Text)

Max Activating Token Index: 78

Text #18

Max Range: 3.2262. Min Range: -3.2262

Max Act: 2.9055. Min Act: -0.1700

Data Index: 7193014 (Open Web Text)

Max Activating Token Index: 281

Text #19

Max Range: 3.2262. Min Range: -3.2262

Max Act: 2.8952. Min Act: -0.1700

Data Index: 1688838 (Open Web Text)

Max Activating Token Index: 327