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

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

Neuron 1311 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0467. Min Range: -4.0467

Max Act: 4.0467. Min Act: -0.1700

Data Index: 248440 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.4991. Min Act: -0.1700

Data Index: 1180237 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.4364. Min Act: -0.1700

Data Index: 320991 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.3580. Min Act: -0.1700

Data Index: 1153762 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.3423. Min Act: -0.1700

Data Index: 660724 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.3423. Min Act: -0.1700

Data Index: 616463 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.3580. Min Act: -0.1700

Data Index: 541110 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.3266. Min Act: -0.1700

Data Index: 120232 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.2795. Min Act: -0.1700

Data Index: 459405 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.2638. Min Act: -0.1700

Data Index: 207737 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.2481. Min Act: -0.1700

Data Index: 182103 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.2952. Min Act: -0.1700

Data Index: 1013680 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.2481. Min Act: -0.1700

Data Index: 1091201 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.2481. Min Act: -0.1700

Data Index: 801310 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.2166. Min Act: -0.1700

Data Index: 1157538 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.2009. Min Act: -0.1700

Data Index: 141379 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.2166. Min Act: -0.1700

Data Index: 423875 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.2009. Min Act: -0.1700

Data Index: 1068368 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.1852. Min Act: -0.1700

Data Index: 227634 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.1852. Min Act: -0.1700

Data Index: 590053 (C4 (Web Text))

Max Activating Token Index: 347