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

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

Neuron 1908 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.8175. Min Act: -0.1700

Data Index: 1188729 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.8018. Min Act: -0.1700

Data Index: 304254 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.7705. Min Act: -0.1700

Data Index: 1099274 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.7862. Min Act: -0.1700

Data Index: 997983 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.7705. Min Act: -0.1700

Data Index: 1313856 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.7549. Min Act: -0.1700

Data Index: 793705 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.7549. Min Act: -0.1700

Data Index: 1256589 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.7705. Min Act: -0.1700

Data Index: 552275 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.7236. Min Act: -0.1700

Data Index: 1118253 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.7236. Min Act: -0.1700

Data Index: 959789 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.7549. Min Act: -0.1700

Data Index: 411060 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.7392. Min Act: -0.1700

Data Index: 418247 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.6923. Min Act: -0.1700

Data Index: 819305 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.7392. Min Act: -0.1700

Data Index: 383653 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.7392. Min Act: -0.1700

Data Index: 942946 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.7236. Min Act: -0.1700

Data Index: 26183 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.7392. Min Act: -0.1700

Data Index: 945302 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.7392. Min Act: -0.1700

Data Index: 22129 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.7549. Min Act: -0.1700

Data Index: 661982 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 3.8175. Min Range: -3.8175

Max Act: 3.7392. Min Act: -0.1700

Data Index: 676220 (C4 (Web Text))

Max Activating Token Index: 551