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

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

Neuron 962 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: 3.1173. Min Range: -3.1173

Max Act: 3.1173. Min Act: -0.1700

Data Index: 1193026 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.0542. Min Act: -0.1700

Data Index: 422626 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.0700. Min Act: -0.1700

Data Index: 194667 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.0542. Min Act: -0.1700

Data Index: 1044254 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.0226. Min Act: -0.1700

Data Index: 1581583 (Python Code)

Max Activating Token Index: 253

Text #5

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.0226. Min Act: -0.1700

Data Index: 155493 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.0542. Min Act: -0.1700

Data Index: 724166 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.0226. Min Act: -0.1700

Data Index: 535787 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.0384. Min Act: -0.1700

Data Index: 1165514 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.0226. Min Act: -0.1700

Data Index: 611527 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.0226. Min Act: -0.1700

Data Index: 807765 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 3.1173. Min Range: -3.1173

Max Act: 2.9910. Min Act: -0.1700

Data Index: 1380998 (Python Code)

Max Activating Token Index: 89

Text #12

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.0068. Min Act: -0.1700

Data Index: 1631103 (Python Code)

Max Activating Token Index: 291

Text #13

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.0068. Min Act: -0.1700

Data Index: 573067 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 3.1173. Min Range: -3.1173

Max Act: 2.9910. Min Act: -0.1700

Data Index: 268717 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.0068. Min Act: -0.1700

Data Index: 1055480 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.0068. Min Act: -0.1700

Data Index: 1263424 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.0068. Min Act: -0.1700

Data Index: 1205538 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 3.1173. Min Range: -3.1173

Max Act: 2.9752. Min Act: -0.1700

Data Index: 871580 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 3.1173. Min Range: -3.1173

Max Act: 2.9752. Min Act: -0.1700

Data Index: 304561 (C4 (Web Text))

Max Activating Token Index: 1011