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

Dataset: Open Web Text

Neuron 1598 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: 3.7717. Min Range: -3.7717

Max Act: 3.7717. Min Act: -0.1700

Data Index: 1678261 (Open Web Text)

Max Activating Token Index: 78

Text #1

Max Range: 3.7717. Min Range: -3.7717

Max Act: 3.7130. Min Act: -0.1700

Data Index: 1678264 (Open Web Text)

Max Activating Token Index: 181

Text #2

Max Range: 3.7717. Min Range: -3.7717

Max Act: 3.6972. Min Act: -0.1700

Data Index: 5677620 (Open Web Text)

Max Activating Token Index: 424

Text #3

Max Range: 3.7717. Min Range: -3.7717

Max Act: 3.6783. Min Act: -0.1700

Data Index: 337355 (Open Web Text)

Max Activating Token Index: 38

Text #4

Max Range: 3.7717. Min Range: -3.7717

Max Act: 3.6549. Min Act: -0.1700

Data Index: 1678254 (Open Web Text)

Max Activating Token Index: 110

Text #5

Max Range: 3.7717. Min Range: -3.7717

Max Act: 3.6583. Min Act: -0.1700

Data Index: 1678269 (Open Web Text)

Max Activating Token Index: 62

Text #6

Max Range: 3.7717. Min Range: -3.7717

Max Act: 3.6369. Min Act: -0.1700

Data Index: 1678259 (Open Web Text)

Max Activating Token Index: 84

Text #7

Max Range: 3.7717. Min Range: -3.7717

Max Act: 3.6249. Min Act: -0.1700

Data Index: 1678271 (Open Web Text)

Max Activating Token Index: 188

Text #8

Max Range: 3.7717. Min Range: -3.7717

Max Act: 3.6425. Min Act: -0.1700

Data Index: 337348 (Open Web Text)

Max Activating Token Index: 96

Text #9

Max Range: 3.7717. Min Range: -3.7717

Max Act: 3.6277. Min Act: -0.1700

Data Index: 1678263 (Open Web Text)

Max Activating Token Index: 148

Text #10

Max Range: 3.7717. Min Range: -3.7717

Max Act: 3.6342. Min Act: -0.1700

Data Index: 1678255 (Open Web Text)

Max Activating Token Index: 118

Text #11

Max Range: 3.7717. Min Range: -3.7717

Max Act: 3.6143. Min Act: -0.1700

Data Index: 5569734 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 3.7717. Min Range: -3.7717

Max Act: 3.6062. Min Act: -0.1700

Data Index: 5677604 (Open Web Text)

Max Activating Token Index: 165

Text #13

Max Range: 3.7717. Min Range: -3.7717

Max Act: 3.5938. Min Act: -0.1700

Data Index: 1678272 (Open Web Text)

Max Activating Token Index: 191

Text #14

Max Range: 3.7717. Min Range: -3.7717

Max Act: 3.6103. Min Act: -0.1700

Data Index: 1678260 (Open Web Text)

Max Activating Token Index: 202

Text #15

Max Range: 3.7717. Min Range: -3.7717

Max Act: 3.5784. Min Act: -0.1700

Data Index: 1292644 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.7717. Min Range: -3.7717

Max Act: 3.5784. Min Act: -0.1700

Data Index: 1391581 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.7717. Min Range: -3.7717

Max Act: 3.5784. Min Act: -0.1700

Data Index: 469585 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.7717. Min Range: -3.7717

Max Act: 3.5784. Min Act: -0.1700

Data Index: 1502739 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 3.7717. Min Range: -3.7717

Max Act: 3.5916. Min Act: -0.1700

Data Index: 1678251 (Open Web Text)

Max Activating Token Index: 374