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

Dataset: Open Web Text

Neuron 1403 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: 3.3289. Min Range: -3.3289

Max Act: 3.3289. Min Act: -0.1700

Data Index: 6571408 (Open Web Text)

Max Activating Token Index: 238

Text #1

Max Range: 3.3289. Min Range: -3.3289

Max Act: 3.2993. Min Act: -0.1700

Data Index: 7958604 (Open Web Text)

Max Activating Token Index: 158

Text #2

Max Range: 3.3289. Min Range: -3.3289

Max Act: 3.2891. Min Act: -0.1700

Data Index: 1764300 (Open Web Text)

Max Activating Token Index: 720

Text #3

Max Range: 3.3289. Min Range: -3.3289

Max Act: 3.2615. Min Act: -0.1700

Data Index: 1573449 (Open Web Text)

Max Activating Token Index: 135

Text #4

Max Range: 3.3289. Min Range: -3.3289

Max Act: 3.2764. Min Act: -0.1700

Data Index: 8573379 (Open Web Text)

Max Activating Token Index: 776

Text #5

Max Range: 3.3289. Min Range: -3.3289

Max Act: 3.2489. Min Act: -0.1700

Data Index: 6507756 (Open Web Text)

Max Activating Token Index: 543

Text #6

Max Range: 3.3289. Min Range: -3.3289

Max Act: 3.2567. Min Act: -0.1700

Data Index: 2390343 (Open Web Text)

Max Activating Token Index: 325

Text #7

Max Range: 3.3289. Min Range: -3.3289

Max Act: 3.2374. Min Act: -0.1700

Data Index: 1076145 (Open Web Text)

Max Activating Token Index: 875

Text #8

Max Range: 3.3289. Min Range: -3.3289

Max Act: 3.2262. Min Act: -0.1700

Data Index: 7076998 (Open Web Text)

Max Activating Token Index: 494

Text #9

Max Range: 3.3289. Min Range: -3.3289

Max Act: 3.2340. Min Act: -0.1700

Data Index: 2286754 (Open Web Text)

Max Activating Token Index: 691

Text #10

Max Range: 3.3289. Min Range: -3.3289

Max Act: 3.2465. Min Act: -0.1700

Data Index: 7184630 (Open Web Text)

Max Activating Token Index: 162

Text #11

Max Range: 3.3289. Min Range: -3.3289

Max Act: 3.2429. Min Act: -0.1700

Data Index: 4259100 (Open Web Text)

Max Activating Token Index: 146

Text #12

Max Range: 3.3289. Min Range: -3.3289

Max Act: 3.2204. Min Act: -0.1700

Data Index: 7209684 (Open Web Text)

Max Activating Token Index: 443

Text #13

Max Range: 3.3289. Min Range: -3.3289

Max Act: 3.2094. Min Act: -0.1700

Data Index: 5653412 (Open Web Text)

Max Activating Token Index: 356

Text #14

Max Range: 3.3289. Min Range: -3.3289

Max Act: 3.2192. Min Act: -0.1700

Data Index: 1225790 (Open Web Text)

Max Activating Token Index: 745

Text #15

Max Range: 3.3289. Min Range: -3.3289

Max Act: 3.2009. Min Act: -0.1700

Data Index: 7204504 (Open Web Text)

Max Activating Token Index: 178

Text #16

Max Range: 3.3289. Min Range: -3.3289

Max Act: 3.2162. Min Act: -0.1700

Data Index: 1597267 (Open Web Text)

Max Activating Token Index: 508

Text #17

Max Range: 3.3289. Min Range: -3.3289

Max Act: 3.2144. Min Act: -0.1700

Data Index: 1836050 (Open Web Text)

Max Activating Token Index: 747

Text #18

Max Range: 3.3289. Min Range: -3.3289

Max Act: 3.2110. Min Act: -0.1700

Data Index: 3921856 (Open Web Text)

Max Activating Token Index: 555

Text #19

Max Range: 3.3289. Min Range: -3.3289

Max Act: 3.2036. Min Act: -0.1700

Data Index: 4433918 (Open Web Text)

Max Activating Token Index: 497