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

Dataset: Open Web Text

Neuron 2585 in Layer 5

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: 3.4964. Min Range: -3.4964

Max Act: 3.4964. Min Act: -0.1700

Data Index: 73163 (Open Web Text)

Max Activating Token Index: 847

Text #1

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.4123. Min Act: -0.1700

Data Index: 8583676 (Open Web Text)

Max Activating Token Index: 538

Text #2

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.3208. Min Act: -0.1700

Data Index: 3951340 (Open Web Text)

Max Activating Token Index: 708

Text #3

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.2559. Min Act: -0.1700

Data Index: 4347216 (Open Web Text)

Max Activating Token Index: 877

Text #4

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.2782. Min Act: -0.1700

Data Index: 5310965 (Open Web Text)

Max Activating Token Index: 442

Text #5

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.2801. Min Act: -0.1700

Data Index: 1697382 (Open Web Text)

Max Activating Token Index: 662

Text #6

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.2518. Min Act: -0.1700

Data Index: 2171819 (Open Web Text)

Max Activating Token Index: 552

Text #7

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.2438. Min Act: -0.1700

Data Index: 4550207 (Open Web Text)

Max Activating Token Index: 358

Text #8

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.2783. Min Act: -0.1700

Data Index: 3099948 (Open Web Text)

Max Activating Token Index: 125

Text #9

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.2337. Min Act: -0.1700

Data Index: 3028241 (Open Web Text)

Max Activating Token Index: 730

Text #10

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.2564. Min Act: -0.1700

Data Index: 84298 (Open Web Text)

Max Activating Token Index: 199

Text #11

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.2263. Min Act: -0.1700

Data Index: 2674455 (Open Web Text)

Max Activating Token Index: 565

Text #12

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.2440. Min Act: -0.1700

Data Index: 8523126 (Open Web Text)

Max Activating Token Index: 623

Text #13

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.2237. Min Act: -0.1700

Data Index: 5886025 (Open Web Text)

Max Activating Token Index: 377

Text #14

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.2208. Min Act: -0.1700

Data Index: 1135115 (Open Web Text)

Max Activating Token Index: 767

Text #15

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.2193. Min Act: -0.1700

Data Index: 6865531 (Open Web Text)

Max Activating Token Index: 235

Text #16

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.1987. Min Act: -0.1700

Data Index: 8537908 (Open Web Text)

Max Activating Token Index: 287

Text #17

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.2150. Min Act: -0.1700

Data Index: 5479158 (Open Web Text)

Max Activating Token Index: 1022

Text #18

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.2059. Min Act: -0.1700

Data Index: 364257 (Open Web Text)

Max Activating Token Index: 258

Text #19

Max Range: 3.4964. Min Range: -3.4964

Max Act: 3.2175. Min Act: -0.1700

Data Index: 7562787 (Open Web Text)

Max Activating Token Index: 820