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

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

Neuron 1191 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3884. Min Range: -3.3884

Max Act: 3.3884. Min Act: -0.1700

Data Index: 1195143 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 3.3884. Min Range: -3.3884

Max Act: 3.3884. Min Act: -0.1700

Data Index: 679632 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 3.3884. Min Range: -3.3884

Max Act: 3.3727. Min Act: -0.1700

Data Index: 1395177 (Python Code)

Max Activating Token Index: 407

Text #3

Max Range: 3.3884. Min Range: -3.3884

Max Act: 3.3570. Min Act: -0.1700

Data Index: 1353125 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 3.3884. Min Range: -3.3884

Max Act: 3.3413. Min Act: -0.1700

Data Index: 152614 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 3.3884. Min Range: -3.3884

Max Act: 3.2628. Min Act: -0.1700

Data Index: 249478 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 3.3884. Min Range: -3.3884

Max Act: 3.2942. Min Act: -0.1700

Data Index: 486964 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 3.3884. Min Range: -3.3884

Max Act: 3.2471. Min Act: -0.1700

Data Index: 1388451 (Python Code)

Max Activating Token Index: 721

Text #8

Max Range: 3.3884. Min Range: -3.3884

Max Act: 3.2314. Min Act: -0.1700

Data Index: 483239 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 3.3884. Min Range: -3.3884

Max Act: 3.2942. Min Act: -0.1700

Data Index: 1092939 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 3.3884. Min Range: -3.3884

Max Act: 3.2157. Min Act: -0.1700

Data Index: 96665 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 3.3884. Min Range: -3.3884

Max Act: 3.1999. Min Act: -0.1700

Data Index: 697460 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 3.3884. Min Range: -3.3884

Max Act: 3.2157. Min Act: -0.1700

Data Index: 1310322 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 3.3884. Min Range: -3.3884

Max Act: 3.2314. Min Act: -0.1700

Data Index: 698987 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 3.3884. Min Range: -3.3884

Max Act: 3.1999. Min Act: -0.1700

Data Index: 31023 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 3.3884. Min Range: -3.3884

Max Act: 3.1685. Min Act: -0.1700

Data Index: 81150 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 3.3884. Min Range: -3.3884

Max Act: 3.1212. Min Act: -0.1700

Data Index: 805506 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 3.3884. Min Range: -3.3884

Max Act: 3.2471. Min Act: -0.1700

Data Index: 1130307 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 3.3884. Min Range: -3.3884

Max Act: 3.1842. Min Act: -0.1700

Data Index: 359068 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 3.3884. Min Range: -3.3884

Max Act: 3.1527. Min Act: -0.1700

Data Index: 1092021 (C4 (Web Text))

Max Activating Token Index: 508