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

Dataset: Open Web Text

Neuron 2520 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: 5.6142. Min Range: -5.6142

Max Act: 5.6142. Min Act: -0.1700

Data Index: 7780887 (Open Web Text)

Max Activating Token Index: 192

Text #1

Max Range: 5.6142. Min Range: -5.6142

Max Act: 5.5135. Min Act: -0.1700

Data Index: 1255699 (Open Web Text)

Max Activating Token Index: 402

Text #2

Max Range: 5.6142. Min Range: -5.6142

Max Act: 5.4792. Min Act: -0.1700

Data Index: 4522901 (Open Web Text)

Max Activating Token Index: 38

Text #3

Max Range: 5.6142. Min Range: -5.6142

Max Act: 5.4380. Min Act: -0.1700

Data Index: 2941328 (Open Web Text)

Max Activating Token Index: 255

Text #4

Max Range: 5.6142. Min Range: -5.6142

Max Act: 5.4465. Min Act: -0.1700

Data Index: 7763836 (Open Web Text)

Max Activating Token Index: 266

Text #5

Max Range: 5.6142. Min Range: -5.6142

Max Act: 5.4053. Min Act: -0.1700

Data Index: 3308925 (Open Web Text)

Max Activating Token Index: 261

Text #6

Max Range: 5.6142. Min Range: -5.6142

Max Act: 5.4072. Min Act: -0.1700

Data Index: 5241639 (Open Web Text)

Max Activating Token Index: 343

Text #7

Max Range: 5.6142. Min Range: -5.6142

Max Act: 5.3425. Min Act: -0.1700

Data Index: 8208171 (Open Web Text)

Max Activating Token Index: 668

Text #8

Max Range: 5.6142. Min Range: -5.6142

Max Act: 5.2933. Min Act: -0.1700

Data Index: 2482316 (Open Web Text)

Max Activating Token Index: 415

Text #9

Max Range: 5.6142. Min Range: -5.6142

Max Act: 5.2356. Min Act: -0.1700

Data Index: 8423333 (Open Web Text)

Max Activating Token Index: 1009

Text #10

Max Range: 5.6142. Min Range: -5.6142

Max Act: 5.2599. Min Act: -0.1700

Data Index: 2485337 (Open Web Text)

Max Activating Token Index: 975

Text #11

Max Range: 5.6142. Min Range: -5.6142

Max Act: 5.2706. Min Act: -0.1700

Data Index: 3998816 (Open Web Text)

Max Activating Token Index: 405

Text #12

Max Range: 5.6142. Min Range: -5.6142

Max Act: 5.2460. Min Act: -0.1700

Data Index: 2154147 (Open Web Text)

Max Activating Token Index: 354

Text #13

Max Range: 5.6142. Min Range: -5.6142

Max Act: 5.2918. Min Act: -0.1700

Data Index: 4532727 (Open Web Text)

Max Activating Token Index: 661

Text #14

Max Range: 5.6142. Min Range: -5.6142

Max Act: 5.2407. Min Act: -0.1700

Data Index: 5067127 (Open Web Text)

Max Activating Token Index: 794

Text #15

Max Range: 5.6142. Min Range: -5.6142

Max Act: 5.2773. Min Act: -0.1700

Data Index: 987252 (Open Web Text)

Max Activating Token Index: 660

Text #16

Max Range: 5.6142. Min Range: -5.6142

Max Act: 5.2496. Min Act: -0.1700

Data Index: 1833637 (Open Web Text)

Max Activating Token Index: 995

Text #17

Max Range: 5.6142. Min Range: -5.6142

Max Act: 5.2453. Min Act: -0.1700

Data Index: 5744030 (Open Web Text)

Max Activating Token Index: 944

Text #18

Max Range: 5.6142. Min Range: -5.6142

Max Act: 5.2944. Min Act: -0.1700

Data Index: 543100 (Open Web Text)

Max Activating Token Index: 927

Text #19

Max Range: 5.6142. Min Range: -5.6142

Max Act: 5.2260. Min Act: -0.1700

Data Index: 4637128 (Open Web Text)

Max Activating Token Index: 585