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

Dataset: Open Web Text

Neuron 732 in Layer 3

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: 4.3212. Min Range: -4.3212

Max Act: 4.2970. Min Act: -0.1700

Data Index: 962671 (Open Web Text)

Max Activating Token Index: 793

Text #1

Max Range: 4.3212. Min Range: -4.3212

Max Act: 4.3212. Min Act: -0.1700

Data Index: 4938001 (Open Web Text)

Max Activating Token Index: 309

Text #2

Max Range: 4.3212. Min Range: -4.3212

Max Act: 4.2209. Min Act: -0.1700

Data Index: 6060674 (Open Web Text)

Max Activating Token Index: 487

Text #3

Max Range: 4.3212. Min Range: -4.3212

Max Act: 4.1926. Min Act: -0.1700

Data Index: 2475505 (Open Web Text)

Max Activating Token Index: 304

Text #4

Max Range: 4.3212. Min Range: -4.3212

Max Act: 4.2045. Min Act: -0.1700

Data Index: 2748766 (Open Web Text)

Max Activating Token Index: 561

Text #5

Max Range: 4.3212. Min Range: -4.3212

Max Act: 4.1630. Min Act: -0.1700

Data Index: 4833151 (Open Web Text)

Max Activating Token Index: 596

Text #6

Max Range: 4.3212. Min Range: -4.3212

Max Act: 4.1171. Min Act: -0.1700

Data Index: 4497244 (Open Web Text)

Max Activating Token Index: 469

Text #7

Max Range: 4.3212. Min Range: -4.3212

Max Act: 4.1805. Min Act: -0.1700

Data Index: 2512717 (Open Web Text)

Max Activating Token Index: 832

Text #8

Max Range: 4.3212. Min Range: -4.3212

Max Act: 4.1669. Min Act: -0.1700

Data Index: 6619627 (Open Web Text)

Max Activating Token Index: 311

Text #9

Max Range: 4.3212. Min Range: -4.3212

Max Act: 4.1551. Min Act: -0.1700

Data Index: 4938003 (Open Web Text)

Max Activating Token Index: 852

Text #10

Max Range: 4.3212. Min Range: -4.3212

Max Act: 4.1770. Min Act: -0.1700

Data Index: 4283596 (Open Web Text)

Max Activating Token Index: 415

Text #11

Max Range: 4.3212. Min Range: -4.3212

Max Act: 4.1552. Min Act: -0.1700

Data Index: 475342 (Open Web Text)

Max Activating Token Index: 215

Text #12

Max Range: 4.3212. Min Range: -4.3212

Max Act: 4.1050. Min Act: -0.1700

Data Index: 8556131 (Open Web Text)

Max Activating Token Index: 12

Text #13

Max Range: 4.3212. Min Range: -4.3212

Max Act: 4.1040. Min Act: -0.1700

Data Index: 4463099 (Open Web Text)

Max Activating Token Index: 468

Text #14

Max Range: 4.3212. Min Range: -4.3212

Max Act: 4.0929. Min Act: -0.1700

Data Index: 287709 (Open Web Text)

Max Activating Token Index: 671

Text #15

Max Range: 4.3212. Min Range: -4.3212

Max Act: 4.1273. Min Act: -0.1700

Data Index: 6785747 (Open Web Text)

Max Activating Token Index: 347

Text #16

Max Range: 4.3212. Min Range: -4.3212

Max Act: 4.1136. Min Act: -0.1700

Data Index: 6740972 (Open Web Text)

Max Activating Token Index: 554

Text #17

Max Range: 4.3212. Min Range: -4.3212

Max Act: 4.1196. Min Act: -0.1700

Data Index: 6037489 (Open Web Text)

Max Activating Token Index: 375

Text #18

Max Range: 4.3212. Min Range: -4.3212

Max Act: 4.0887. Min Act: -0.1700

Data Index: 2748770 (Open Web Text)

Max Activating Token Index: 1014

Text #19

Max Range: 4.3212. Min Range: -4.3212

Max Act: 4.1318. Min Act: -0.1700

Data Index: 5377730 (Open Web Text)

Max Activating Token Index: 14