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

Dataset: Open Web Text

Neuron 1999 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: 4.4048. Min Range: -4.4048

Max Act: 4.4048. Min Act: -0.1700

Data Index: 5967041 (Open Web Text)

Max Activating Token Index: 89

Text #1

Max Range: 4.4048. Min Range: -4.4048

Max Act: 4.3894. Min Act: -0.1700

Data Index: 7503039 (Open Web Text)

Max Activating Token Index: 325

Text #2

Max Range: 4.4048. Min Range: -4.4048

Max Act: 4.3847. Min Act: -0.1700

Data Index: 4683282 (Open Web Text)

Max Activating Token Index: 453

Text #3

Max Range: 4.4048. Min Range: -4.4048

Max Act: 4.3424. Min Act: -0.1700

Data Index: 5221252 (Open Web Text)

Max Activating Token Index: 137

Text #4

Max Range: 4.4048. Min Range: -4.4048

Max Act: 4.3132. Min Act: -0.1700

Data Index: 1282105 (Open Web Text)

Max Activating Token Index: 170

Text #5

Max Range: 4.4048. Min Range: -4.4048

Max Act: 4.3186. Min Act: -0.1700

Data Index: 7985933 (Open Web Text)

Max Activating Token Index: 936

Text #6

Max Range: 4.4048. Min Range: -4.4048

Max Act: 4.3221. Min Act: -0.1700

Data Index: 8594651 (Open Web Text)

Max Activating Token Index: 614

Text #7

Max Range: 4.4048. Min Range: -4.4048

Max Act: 4.2924. Min Act: -0.1700

Data Index: 4846411 (Open Web Text)

Max Activating Token Index: 253

Text #8

Max Range: 4.4048. Min Range: -4.4048

Max Act: 4.2968. Min Act: -0.1700

Data Index: 5967042 (Open Web Text)

Max Activating Token Index: 82

Text #9

Max Range: 4.4048. Min Range: -4.4048

Max Act: 4.3159. Min Act: -0.1700

Data Index: 1570171 (Open Web Text)

Max Activating Token Index: 479

Text #10

Max Range: 4.4048. Min Range: -4.4048

Max Act: 4.3163. Min Act: -0.1700

Data Index: 4461766 (Open Web Text)

Max Activating Token Index: 561

Text #11

Max Range: 4.4048. Min Range: -4.4048

Max Act: 4.2381. Min Act: -0.1700

Data Index: 2221778 (Open Web Text)

Max Activating Token Index: 269

Text #12

Max Range: 4.4048. Min Range: -4.4048

Max Act: 4.2487. Min Act: -0.1700

Data Index: 7485138 (Open Web Text)

Max Activating Token Index: 265

Text #13

Max Range: 4.4048. Min Range: -4.4048

Max Act: 4.2826. Min Act: -0.1700

Data Index: 159698 (Open Web Text)

Max Activating Token Index: 147

Text #14

Max Range: 4.4048. Min Range: -4.4048

Max Act: 4.2745. Min Act: -0.1700

Data Index: 2663650 (Open Web Text)

Max Activating Token Index: 441

Text #15

Max Range: 4.4048. Min Range: -4.4048

Max Act: 4.2222. Min Act: -0.1700

Data Index: 5512782 (Open Web Text)

Max Activating Token Index: 16

Text #16

Max Range: 4.4048. Min Range: -4.4048

Max Act: 4.2265. Min Act: -0.1700

Data Index: 7962501 (Open Web Text)

Max Activating Token Index: 730

Text #17

Max Range: 4.4048. Min Range: -4.4048

Max Act: 4.1940. Min Act: -0.1700

Data Index: 6146025 (Open Web Text)

Max Activating Token Index: 448

Text #18

Max Range: 4.4048. Min Range: -4.4048

Max Act: 4.1798. Min Act: -0.1700

Data Index: 16767 (Open Web Text)

Max Activating Token Index: 594

Text #19

Max Range: 4.4048. Min Range: -4.4048

Max Act: 4.1792. Min Act: -0.1700

Data Index: 6487162 (Open Web Text)

Max Activating Token Index: 791