Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 253 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.5786. Min Range: -3.5786

Max Act: 3.5786. Min Act: -0.1700

Data Index: 1081774 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 3.5786. Min Range: -3.5786

Max Act: 3.5008. Min Act: -0.1700

Data Index: 1351773 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 3.5786. Min Range: -3.5786

Max Act: 3.4004. Min Act: -0.1700

Data Index: 857070 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 3.5786. Min Range: -3.5786

Max Act: 3.3774. Min Act: -0.1700

Data Index: 177949 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 3.5786. Min Range: -3.5786

Max Act: 3.3798. Min Act: -0.1700

Data Index: 313290 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 3.5786. Min Range: -3.5786

Max Act: 3.3850. Min Act: -0.1700

Data Index: 1043060 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 3.5786. Min Range: -3.5786

Max Act: 3.3627. Min Act: -0.1700

Data Index: 617418 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 3.5786. Min Range: -3.5786

Max Act: 3.3594. Min Act: -0.1700

Data Index: 1236990 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 3.5786. Min Range: -3.5786

Max Act: 3.3811. Min Act: -0.1700

Data Index: 1356727 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 3.5786. Min Range: -3.5786

Max Act: 3.3386. Min Act: -0.1700

Data Index: 654383 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 3.5786. Min Range: -3.5786

Max Act: 3.3519. Min Act: -0.1700

Data Index: 1331187 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 3.5786. Min Range: -3.5786

Max Act: 3.3460. Min Act: -0.1700

Data Index: 591982 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 3.5786. Min Range: -3.5786

Max Act: 3.3475. Min Act: -0.1700

Data Index: 377262 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 3.5786. Min Range: -3.5786

Max Act: 3.3412. Min Act: -0.1700

Data Index: 545125 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 3.5786. Min Range: -3.5786

Max Act: 3.3682. Min Act: -0.1700

Data Index: 49825 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 3.5786. Min Range: -3.5786

Max Act: 3.3447. Min Act: -0.1700

Data Index: 567894 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 3.5786. Min Range: -3.5786

Max Act: 3.3499. Min Act: -0.1700

Data Index: 1128068 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 3.5786. Min Range: -3.5786

Max Act: 3.3447. Min Act: -0.1700

Data Index: 798308 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 3.5786. Min Range: -3.5786

Max Act: 3.3286. Min Act: -0.1700

Data Index: 1232427 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 3.5786. Min Range: -3.5786

Max Act: 3.3301. Min Act: -0.1700

Data Index: 982747 (C4 (Web Text))

Max Activating Token Index: 682