Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1992 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.3474. Min Range: -5.3474

Max Act: 5.3474. Min Act: -0.1700

Data Index: 367529 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 5.3474. Min Range: -5.3474

Max Act: 5.1286. Min Act: -0.1700

Data Index: 439502 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 5.3474. Min Range: -5.3474

Max Act: 5.0661. Min Act: -0.1700

Data Index: 181722 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 5.3474. Min Range: -5.3474

Max Act: 5.1599. Min Act: -0.1700

Data Index: 738685 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 5.3474. Min Range: -5.3474

Max Act: 5.0974. Min Act: -0.1700

Data Index: 999797 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 5.3474. Min Range: -5.3474

Max Act: 5.1286. Min Act: -0.1700

Data Index: 578180 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 5.3474. Min Range: -5.3474

Max Act: 5.0974. Min Act: -0.1700

Data Index: 184063 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 5.3474. Min Range: -5.3474

Max Act: 5.1286. Min Act: -0.1700

Data Index: 79558 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 5.3474. Min Range: -5.3474

Max Act: 5.0036. Min Act: -0.1700

Data Index: 279574 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 5.3474. Min Range: -5.3474

Max Act: 5.0661. Min Act: -0.1700

Data Index: 317451 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 5.3474. Min Range: -5.3474

Max Act: 5.0661. Min Act: -0.1700

Data Index: 1018374 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 5.3474. Min Range: -5.3474

Max Act: 5.0349. Min Act: -0.1700

Data Index: 1169156 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 5.3474. Min Range: -5.3474

Max Act: 5.0349. Min Act: -0.1700

Data Index: 445285 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 5.3474. Min Range: -5.3474

Max Act: 4.9724. Min Act: -0.1700

Data Index: 278330 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 5.3474. Min Range: -5.3474

Max Act: 5.0036. Min Act: -0.1700

Data Index: 566164 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 5.3474. Min Range: -5.3474

Max Act: 4.9724. Min Act: -0.1700

Data Index: 1109845 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 5.3474. Min Range: -5.3474

Max Act: 5.0036. Min Act: -0.1700

Data Index: 992472 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 5.3474. Min Range: -5.3474

Max Act: 5.0036. Min Act: -0.1700

Data Index: 828993 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 5.3474. Min Range: -5.3474

Max Act: 4.9411. Min Act: -0.1700

Data Index: 166367 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 5.3474. Min Range: -5.3474

Max Act: 5.0036. Min Act: -0.1700

Data Index: 359409 (C4 (Web Text))

Max Activating Token Index: 528