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

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

Neuron 1981 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: 3.4982. Min Range: -3.4982

Max Act: 3.4982. Min Act: -0.1700

Data Index: 627534 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.4512. Min Act: -0.1700

Data Index: 329150 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.3885. Min Act: -0.1700

Data Index: 253474 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.4199. Min Act: -0.1700

Data Index: 851212 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.4512. Min Act: -0.1700

Data Index: 897781 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.4042. Min Act: -0.1700

Data Index: 942428 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.3414. Min Act: -0.1700

Data Index: 318617 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.3100. Min Act: -0.1700

Data Index: 1121920 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2786. Min Act: -0.1700

Data Index: 260753 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.3571. Min Act: -0.1700

Data Index: 1343407 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2943. Min Act: -0.1700

Data Index: 484491 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.3100. Min Act: -0.1700

Data Index: 851438 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2629. Min Act: -0.1700

Data Index: 1283088 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.3571. Min Act: -0.1700

Data Index: 414485 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2629. Min Act: -0.1700

Data Index: 285197 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.1843. Min Act: -0.1700

Data Index: 383049 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2472. Min Act: -0.1700

Data Index: 88612 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2472. Min Act: -0.1700

Data Index: 614547 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2315. Min Act: -0.1700

Data Index: 781775 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 3.4982. Min Range: -3.4982

Max Act: 3.2315. Min Act: -0.1700

Data Index: 967084 (C4 (Web Text))

Max Activating Token Index: 120