Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 385 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.6263. Min Act: -0.1700

Data Index: 867767 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.6263. Min Act: -0.1700

Data Index: 369441 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.4853. Min Act: -0.1700

Data Index: 1205196 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.5010. Min Act: -0.1700

Data Index: 51016 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.4696. Min Act: -0.1700

Data Index: 852571 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.4540. Min Act: -0.1700

Data Index: 214317 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.4069. Min Act: -0.1700

Data Index: 439651 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.4069. Min Act: -0.1700

Data Index: 429793 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.4069. Min Act: -0.1700

Data Index: 166268 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.3599. Min Act: -0.1700

Data Index: 1176086 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.3442. Min Act: -0.1700

Data Index: 21098 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.4069. Min Act: -0.1700

Data Index: 713998 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.4226. Min Act: -0.1700

Data Index: 766774 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.3128. Min Act: -0.1700

Data Index: 938152 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.2814. Min Act: -0.1700

Data Index: 914400 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.2971. Min Act: -0.1700

Data Index: 685992 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.2342. Min Act: -0.1700

Data Index: 1130098 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.2185. Min Act: -0.1700

Data Index: 904971 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.3128. Min Act: -0.1700

Data Index: 1247283 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 3.6263. Min Range: -3.6263

Max Act: 3.2185. Min Act: -0.1700

Data Index: 1343413 (C4 (Web Text))

Max Activating Token Index: 129