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

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

Neuron 1150 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8598. Min Range: -3.8598

Max Act: 3.8598. Min Act: -0.1700

Data Index: 835815 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 3.8598. Min Range: -3.8598

Max Act: 3.7660. Min Act: -0.1700

Data Index: 1204865 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 3.8598. Min Range: -3.8598

Max Act: 3.7816. Min Act: -0.1700

Data Index: 601001 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 3.8598. Min Range: -3.8598

Max Act: 3.7347. Min Act: -0.1700

Data Index: 140234 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 3.8598. Min Range: -3.8598

Max Act: 3.7034. Min Act: -0.1700

Data Index: 1735 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 3.8598. Min Range: -3.8598

Max Act: 3.7034. Min Act: -0.1700

Data Index: 521621 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 3.8598. Min Range: -3.8598

Max Act: 3.7034. Min Act: -0.1700

Data Index: 911173 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 3.8598. Min Range: -3.8598

Max Act: 3.7191. Min Act: -0.1700

Data Index: 1096953 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 3.8598. Min Range: -3.8598

Max Act: 3.6878. Min Act: -0.1700

Data Index: 539273 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 3.8598. Min Range: -3.8598

Max Act: 3.6408. Min Act: -0.1700

Data Index: 950141 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 3.8598. Min Range: -3.8598

Max Act: 3.6721. Min Act: -0.1700

Data Index: 358271 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 3.8598. Min Range: -3.8598

Max Act: 3.6565. Min Act: -0.1700

Data Index: 666734 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 3.8598. Min Range: -3.8598

Max Act: 3.6878. Min Act: -0.1700

Data Index: 1037754 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 3.8598. Min Range: -3.8598

Max Act: 3.6565. Min Act: -0.1700

Data Index: 839698 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 3.8598. Min Range: -3.8598

Max Act: 3.6408. Min Act: -0.1700

Data Index: 831165 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 3.8598. Min Range: -3.8598

Max Act: 3.6878. Min Act: -0.1700

Data Index: 1242488 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 3.8598. Min Range: -3.8598

Max Act: 3.6408. Min Act: -0.1700

Data Index: 952169 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 3.8598. Min Range: -3.8598

Max Act: 3.6565. Min Act: -0.1700

Data Index: 167575 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 3.8598. Min Range: -3.8598

Max Act: 3.5939. Min Act: -0.1700

Data Index: 756362 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 3.8598. Min Range: -3.8598

Max Act: 3.6095. Min Act: -0.1700

Data Index: 843379 (C4 (Web Text))

Max Activating Token Index: 578