Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 895 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.4461. Min Range: -5.4461

Max Act: 5.4461. Min Act: -0.1700

Data Index: 1013261 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 5.4461. Min Range: -5.4461

Max Act: 5.4461. Min Act: -0.1700

Data Index: 1257276 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 5.4461. Min Range: -5.4461

Max Act: 5.3524. Min Act: -0.1700

Data Index: 1090396 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 5.4461. Min Range: -5.4461

Max Act: 5.4461. Min Act: -0.1700

Data Index: 925266 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 5.4461. Min Range: -5.4461

Max Act: 5.3836. Min Act: -0.1700

Data Index: 832063 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 5.4461. Min Range: -5.4461

Max Act: 5.2586. Min Act: -0.1700

Data Index: 1334065 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 5.4461. Min Range: -5.4461

Max Act: 5.1961. Min Act: -0.1700

Data Index: 1278101 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 5.4461. Min Range: -5.4461

Max Act: 5.1961. Min Act: -0.1700

Data Index: 1099706 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 5.4461. Min Range: -5.4461

Max Act: 5.2274. Min Act: -0.1700

Data Index: 1282257 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 5.4461. Min Range: -5.4461

Max Act: 5.3211. Min Act: -0.1700

Data Index: 764525 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 5.4461. Min Range: -5.4461

Max Act: 5.1961. Min Act: -0.1700

Data Index: 481817 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 5.4461. Min Range: -5.4461

Max Act: 5.2586. Min Act: -0.1700

Data Index: 772485 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 5.4461. Min Range: -5.4461

Max Act: 5.1961. Min Act: -0.1700

Data Index: 841800 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 5.4461. Min Range: -5.4461

Max Act: 5.2586. Min Act: -0.1700

Data Index: 616197 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 5.4461. Min Range: -5.4461

Max Act: 5.2586. Min Act: -0.1700

Data Index: 1122113 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 5.4461. Min Range: -5.4461

Max Act: 5.1961. Min Act: -0.1700

Data Index: 1042146 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 5.4461. Min Range: -5.4461

Max Act: 5.1649. Min Act: -0.1700

Data Index: 290909 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 5.4461. Min Range: -5.4461

Max Act: 5.2274. Min Act: -0.1700

Data Index: 278358 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 5.4461. Min Range: -5.4461

Max Act: 5.1961. Min Act: -0.1700

Data Index: 102586 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 5.4461. Min Range: -5.4461

Max Act: 5.1649. Min Act: -0.1700

Data Index: 521597 (C4 (Web Text))

Max Activating Token Index: 825