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

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

Neuron 1888 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: 3.6198. Min Range: -3.6198

Max Act: 3.6198. Min Act: -0.1700

Data Index: 180376 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.5885. Min Act: -0.1700

Data Index: 120005 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.5728. Min Act: -0.1700

Data Index: 117069 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.5415. Min Act: -0.1700

Data Index: 241555 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.5102. Min Act: -0.1700

Data Index: 1285037 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.5415. Min Act: -0.1700

Data Index: 890402 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.5258. Min Act: -0.1700

Data Index: 506304 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.5572. Min Act: -0.1700

Data Index: 292494 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.4788. Min Act: -0.1700

Data Index: 792658 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.4788. Min Act: -0.1700

Data Index: 1234861 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.5258. Min Act: -0.1700

Data Index: 419420 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.5102. Min Act: -0.1700

Data Index: 580193 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.4945. Min Act: -0.1700

Data Index: 595348 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.4945. Min Act: -0.1700

Data Index: 577824 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.5102. Min Act: -0.1700

Data Index: 807858 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.4475. Min Act: -0.1700

Data Index: 1034586 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.4788. Min Act: -0.1700

Data Index: 1050362 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.4788. Min Act: -0.1700

Data Index: 358271 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.4318. Min Act: -0.1700

Data Index: 551373 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 3.6198. Min Range: -3.6198

Max Act: 3.4788. Min Act: -0.1700

Data Index: 1810 (C4 (Web Text))

Max Activating Token Index: 1022