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

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

Neuron 371 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: 3.5982. Min Range: -3.5982

Max Act: 3.5982. Min Act: -0.1700

Data Index: 78034 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 3.5982. Min Range: -3.5982

Max Act: 3.4101. Min Act: -0.1700

Data Index: 1095945 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 3.5982. Min Range: -3.5982

Max Act: 3.4728. Min Act: -0.1700

Data Index: 716271 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 3.5982. Min Range: -3.5982

Max Act: 3.5042. Min Act: -0.1700

Data Index: 862066 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 3.5982. Min Range: -3.5982

Max Act: 3.4415. Min Act: -0.1700

Data Index: 830058 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 3.5982. Min Range: -3.5982

Max Act: 3.4101. Min Act: -0.1700

Data Index: 1001952 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 3.5982. Min Range: -3.5982

Max Act: 3.3160. Min Act: -0.1700

Data Index: 811551 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 3.5982. Min Range: -3.5982

Max Act: 3.3788. Min Act: -0.1700

Data Index: 401009 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 3.5982. Min Range: -3.5982

Max Act: 3.3160. Min Act: -0.1700

Data Index: 646533 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 3.5982. Min Range: -3.5982

Max Act: 3.3160. Min Act: -0.1700

Data Index: 236971 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 3.5982. Min Range: -3.5982

Max Act: 3.3474. Min Act: -0.1700

Data Index: 1035489 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 3.5982. Min Range: -3.5982

Max Act: 3.2846. Min Act: -0.1700

Data Index: 29665 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 3.5982. Min Range: -3.5982

Max Act: 3.3474. Min Act: -0.1700

Data Index: 610961 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 3.5982. Min Range: -3.5982

Max Act: 3.3160. Min Act: -0.1700

Data Index: 403877 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 3.5982. Min Range: -3.5982

Max Act: 3.3160. Min Act: -0.1700

Data Index: 65573 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 3.5982. Min Range: -3.5982

Max Act: 3.2846. Min Act: -0.1700

Data Index: 969244 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 3.5982. Min Range: -3.5982

Max Act: 3.2217. Min Act: -0.1700

Data Index: 405505 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 3.5982. Min Range: -3.5982

Max Act: 3.2846. Min Act: -0.1700

Data Index: 784943 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 3.5982. Min Range: -3.5982

Max Act: 3.2531. Min Act: -0.1700

Data Index: 156032 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 3.5982. Min Range: -3.5982

Max Act: 3.2846. Min Act: -0.1700

Data Index: 441267 (C4 (Web Text))

Max Activating Token Index: 410