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

Dataset: Open Web Text

Neuron 1870 in Layer 6

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: 3.5205. Min Range: -3.5205

Max Act: 3.5205. Min Act: -0.1700

Data Index: 8369978 (Open Web Text)

Max Activating Token Index: 975

Text #1

Max Range: 3.5205. Min Range: -3.5205

Max Act: 3.4870. Min Act: -0.1700

Data Index: 5203607 (Open Web Text)

Max Activating Token Index: 318

Text #2

Max Range: 3.5205. Min Range: -3.5205

Max Act: 3.4736. Min Act: -0.1700

Data Index: 3636324 (Open Web Text)

Max Activating Token Index: 647

Text #3

Max Range: 3.5205. Min Range: -3.5205

Max Act: 3.4630. Min Act: -0.1700

Data Index: 1258653 (Open Web Text)

Max Activating Token Index: 882

Text #4

Max Range: 3.5205. Min Range: -3.5205

Max Act: 3.4654. Min Act: -0.1700

Data Index: 5671102 (Open Web Text)

Max Activating Token Index: 373

Text #5

Max Range: 3.5205. Min Range: -3.5205

Max Act: 3.4438. Min Act: -0.1700

Data Index: 3907515 (Open Web Text)

Max Activating Token Index: 752

Text #6

Max Range: 3.5205. Min Range: -3.5205

Max Act: 3.4398. Min Act: -0.1700

Data Index: 2167210 (Open Web Text)

Max Activating Token Index: 713

Text #7

Max Range: 3.5205. Min Range: -3.5205

Max Act: 3.4277. Min Act: -0.1700

Data Index: 5269916 (Open Web Text)

Max Activating Token Index: 426

Text #8

Max Range: 3.5205. Min Range: -3.5205

Max Act: 3.4057. Min Act: -0.1700

Data Index: 7885815 (Open Web Text)

Max Activating Token Index: 850

Text #9

Max Range: 3.5205. Min Range: -3.5205

Max Act: 3.4078. Min Act: -0.1700

Data Index: 611989 (Open Web Text)

Max Activating Token Index: 269

Text #10

Max Range: 3.5205. Min Range: -3.5205

Max Act: 3.4158. Min Act: -0.1700

Data Index: 8629458 (Open Web Text)

Max Activating Token Index: 631

Text #11

Max Range: 3.5205. Min Range: -3.5205

Max Act: 3.4052. Min Act: -0.1700

Data Index: 4500270 (Open Web Text)

Max Activating Token Index: 557

Text #12

Max Range: 3.5205. Min Range: -3.5205

Max Act: 3.4002. Min Act: -0.1700

Data Index: 5537662 (Open Web Text)

Max Activating Token Index: 375

Text #13

Max Range: 3.5205. Min Range: -3.5205

Max Act: 3.3949. Min Act: -0.1700

Data Index: 7191031 (Open Web Text)

Max Activating Token Index: 819

Text #14

Max Range: 3.5205. Min Range: -3.5205

Max Act: 3.3912. Min Act: -0.1700

Data Index: 583303 (Open Web Text)

Max Activating Token Index: 470

Text #15

Max Range: 3.5205. Min Range: -3.5205

Max Act: 3.3812. Min Act: -0.1700

Data Index: 1051987 (Open Web Text)

Max Activating Token Index: 920

Text #16

Max Range: 3.5205. Min Range: -3.5205

Max Act: 3.3763. Min Act: -0.1700

Data Index: 5881978 (Open Web Text)

Max Activating Token Index: 615

Text #17

Max Range: 3.5205. Min Range: -3.5205

Max Act: 3.3988. Min Act: -0.1700

Data Index: 3862998 (Open Web Text)

Max Activating Token Index: 727

Text #18

Max Range: 3.5205. Min Range: -3.5205

Max Act: 3.3831. Min Act: -0.1700

Data Index: 7858656 (Open Web Text)

Max Activating Token Index: 906

Text #19

Max Range: 3.5205. Min Range: -3.5205

Max Act: 3.3784. Min Act: -0.1700

Data Index: 5135848 (Open Web Text)

Max Activating Token Index: 471