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

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

Neuron 1051 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: 3.4121. Min Range: -3.4121

Max Act: 3.4121. Min Act: -0.1700

Data Index: 210178 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 3.4121. Min Range: -3.4121

Max Act: 3.3337. Min Act: -0.1700

Data Index: 346312 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 3.4121. Min Range: -3.4121

Max Act: 3.3023. Min Act: -0.1700

Data Index: 182339 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 3.4121. Min Range: -3.4121

Max Act: 3.3023. Min Act: -0.1700

Data Index: 311624 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 3.4121. Min Range: -3.4121

Max Act: 3.2866. Min Act: -0.1700

Data Index: 611210 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 3.4121. Min Range: -3.4121

Max Act: 3.2709. Min Act: -0.1700

Data Index: 335199 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 3.4121. Min Range: -3.4121

Max Act: 3.2552. Min Act: -0.1700

Data Index: 250254 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 3.4121. Min Range: -3.4121

Max Act: 3.2394. Min Act: -0.1700

Data Index: 1125247 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 3.4121. Min Range: -3.4121

Max Act: 3.2394. Min Act: -0.1700

Data Index: 28938 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 3.4121. Min Range: -3.4121

Max Act: 3.2552. Min Act: -0.1700

Data Index: 1237586 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 3.4121. Min Range: -3.4121

Max Act: 3.2394. Min Act: -0.1700

Data Index: 1342735 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 3.4121. Min Range: -3.4121

Max Act: 3.2237. Min Act: -0.1700

Data Index: 984009 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 3.4121. Min Range: -3.4121

Max Act: 3.2080. Min Act: -0.1700

Data Index: 1340220 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 3.4121. Min Range: -3.4121

Max Act: 3.2080. Min Act: -0.1700

Data Index: 1278269 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 3.4121. Min Range: -3.4121

Max Act: 3.2237. Min Act: -0.1700

Data Index: 813971 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 3.4121. Min Range: -3.4121

Max Act: 3.1922. Min Act: -0.1700

Data Index: 8349 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 3.4121. Min Range: -3.4121

Max Act: 3.2080. Min Act: -0.1700

Data Index: 289570 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 3.4121. Min Range: -3.4121

Max Act: 3.1922. Min Act: -0.1700

Data Index: 671009 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 3.4121. Min Range: -3.4121

Max Act: 3.1922. Min Act: -0.1700

Data Index: 709545 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 3.4121. Min Range: -3.4121

Max Act: 3.1765. Min Act: -0.1700

Data Index: 814187 (C4 (Web Text))

Max Activating Token Index: 245