Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1728 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3037. Min Range: -3.3037

Max Act: 3.3037. Min Act: -0.1700

Data Index: 1518301 (Python Code)

Max Activating Token Index: 875

Text #1

Max Range: 3.3037. Min Range: -3.3037

Max Act: 3.2094. Min Act: -0.1700

Data Index: 1646448 (Python Code)

Max Activating Token Index: 528

Text #2

Max Range: 3.3037. Min Range: -3.3037

Max Act: 3.2408. Min Act: -0.1700

Data Index: 469616 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 3.3037. Min Range: -3.3037

Max Act: 3.2565. Min Act: -0.1700

Data Index: 1051875 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 3.3037. Min Range: -3.3037

Max Act: 3.1936. Min Act: -0.1700

Data Index: 14146 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 3.3037. Min Range: -3.3037

Max Act: 3.1936. Min Act: -0.1700

Data Index: 494872 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 3.3037. Min Range: -3.3037

Max Act: 3.1936. Min Act: -0.1700

Data Index: 618186 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 3.3037. Min Range: -3.3037

Max Act: 3.1936. Min Act: -0.1700

Data Index: 78919 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 3.3037. Min Range: -3.3037

Max Act: 3.1307. Min Act: -0.1700

Data Index: 771472 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 3.3037. Min Range: -3.3037

Max Act: 3.1307. Min Act: -0.1700

Data Index: 1552694 (Python Code)

Max Activating Token Index: 518

Text #10

Max Range: 3.3037. Min Range: -3.3037

Max Act: 3.1307. Min Act: -0.1700

Data Index: 1161578 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 3.3037. Min Range: -3.3037

Max Act: 3.0991. Min Act: -0.1700

Data Index: 1448767 (Python Code)

Max Activating Token Index: 934

Text #12

Max Range: 3.3037. Min Range: -3.3037

Max Act: 3.1307. Min Act: -0.1700

Data Index: 719517 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 3.3037. Min Range: -3.3037

Max Act: 3.0991. Min Act: -0.1700

Data Index: 1287572 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 3.3037. Min Range: -3.3037

Max Act: 3.1149. Min Act: -0.1700

Data Index: 57734 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 3.3037. Min Range: -3.3037

Max Act: 3.1149. Min Act: -0.1700

Data Index: 1012741 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 3.3037. Min Range: -3.3037

Max Act: 3.1149. Min Act: -0.1700

Data Index: 282492 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 3.3037. Min Range: -3.3037

Max Act: 3.0991. Min Act: -0.1700

Data Index: 864063 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 3.3037. Min Range: -3.3037

Max Act: 3.0991. Min Act: -0.1700

Data Index: 508454 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 3.3037. Min Range: -3.3037

Max Act: 3.0991. Min Act: -0.1700

Data Index: 406610 (C4 (Web Text))

Max Activating Token Index: 639