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

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

Neuron 1702 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.5138. Min Act: -0.1700

Data Index: 920759 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.4511. Min Act: -0.1700

Data Index: 1032798 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.4041. Min Act: -0.1700

Data Index: 364847 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.4197. Min Act: -0.1700

Data Index: 11344 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.3727. Min Act: -0.1700

Data Index: 509135 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.4354. Min Act: -0.1700

Data Index: 125289 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.4197. Min Act: -0.1700

Data Index: 1021288 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.4197. Min Act: -0.1700

Data Index: 1271872 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.4041. Min Act: -0.1700

Data Index: 551946 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.3570. Min Act: -0.1700

Data Index: 884584 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.3727. Min Act: -0.1700

Data Index: 1259258 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.3727. Min Act: -0.1700

Data Index: 1139856 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.3727. Min Act: -0.1700

Data Index: 385034 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.3570. Min Act: -0.1700

Data Index: 1189170 (C4 (Web Text))

Max Activating Token Index: 293

Text #14

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.3727. Min Act: -0.1700

Data Index: 399543 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.3413. Min Act: -0.1700

Data Index: 1095114 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.3099. Min Act: -0.1700

Data Index: 219221 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.3413. Min Act: -0.1700

Data Index: 1091445 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.2942. Min Act: -0.1700

Data Index: 111466 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.3413. Min Act: -0.1700

Data Index: 313871 (C4 (Web Text))

Max Activating Token Index: 851