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

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

Neuron 747 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: 3.7514. Min Range: -3.7514

Max Act: 3.7514. Min Act: -0.1700

Data Index: 293778 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.5323. Min Act: -0.1700

Data Index: 419143 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.5323. Min Act: -0.1700

Data Index: 231415 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.5323. Min Act: -0.1700

Data Index: 257816 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.5323. Min Act: -0.1700

Data Index: 399550 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.5009. Min Act: -0.1700

Data Index: 992944 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.5009. Min Act: -0.1700

Data Index: 515964 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.4696. Min Act: -0.1700

Data Index: 778194 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.4696. Min Act: -0.1700

Data Index: 1062214 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.4696. Min Act: -0.1700

Data Index: 397905 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.4069. Min Act: -0.1700

Data Index: 1140316 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.4382. Min Act: -0.1700

Data Index: 312907 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.4382. Min Act: -0.1700

Data Index: 152557 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.4696. Min Act: -0.1700

Data Index: 609558 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.4382. Min Act: -0.1700

Data Index: 194745 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.4382. Min Act: -0.1700

Data Index: 208026 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.4069. Min Act: -0.1700

Data Index: 229289 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.4069. Min Act: -0.1700

Data Index: 899997 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.3755. Min Act: -0.1700

Data Index: 572328 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 3.7514. Min Range: -3.7514

Max Act: 3.4382. Min Act: -0.1700

Data Index: 7283 (C4 (Web Text))

Max Activating Token Index: 135