Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 10 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4602. Min Range: -3.4602

Max Act: 3.4602. Min Act: -0.1700

Data Index: 120418 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 3.4602. Min Range: -3.4602

Max Act: 3.4602. Min Act: -0.1700

Data Index: 428361 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 3.4602. Min Range: -3.4602

Max Act: 3.4289. Min Act: -0.1700

Data Index: 115401 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 3.4602. Min Range: -3.4602

Max Act: 3.3975. Min Act: -0.1700

Data Index: 387445 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 3.4602. Min Range: -3.4602

Max Act: 3.3975. Min Act: -0.1700

Data Index: 1119723 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 3.4602. Min Range: -3.4602

Max Act: 3.3661. Min Act: -0.1700

Data Index: 1305042 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 3.4602. Min Range: -3.4602

Max Act: 3.3661. Min Act: -0.1700

Data Index: 1033903 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 3.4602. Min Range: -3.4602

Max Act: 3.3661. Min Act: -0.1700

Data Index: 1062376 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 3.4602. Min Range: -3.4602

Max Act: 3.3661. Min Act: -0.1700

Data Index: 1126102 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 3.4602. Min Range: -3.4602

Max Act: 3.3661. Min Act: -0.1700

Data Index: 327970 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 3.4602. Min Range: -3.4602

Max Act: 3.3347. Min Act: -0.1700

Data Index: 410347 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 3.4602. Min Range: -3.4602

Max Act: 3.3504. Min Act: -0.1700

Data Index: 415009 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 3.4602. Min Range: -3.4602

Max Act: 3.3347. Min Act: -0.1700

Data Index: 573269 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 3.4602. Min Range: -3.4602

Max Act: 3.3347. Min Act: -0.1700

Data Index: 325254 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 3.4602. Min Range: -3.4602

Max Act: 3.3347. Min Act: -0.1700

Data Index: 1188621 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 3.4602. Min Range: -3.4602

Max Act: 3.3190. Min Act: -0.1700

Data Index: 458914 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 3.4602. Min Range: -3.4602

Max Act: 3.3033. Min Act: -0.1700

Data Index: 250912 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 3.4602. Min Range: -3.4602

Max Act: 3.2876. Min Act: -0.1700

Data Index: 264321 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 3.4602. Min Range: -3.4602

Max Act: 3.2876. Min Act: -0.1700

Data Index: 9762 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 3.4602. Min Range: -3.4602

Max Act: 3.2719. Min Act: -0.1700

Data Index: 912415 (C4 (Web Text))

Max Activating Token Index: 863