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

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

Neuron 1913 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.9882. Min Range: -5.9882

Max Act: 5.9882. Min Act: -0.1700

Data Index: 717103 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 5.9882. Min Range: -5.9882

Max Act: 5.9569. Min Act: -0.1700

Data Index: 990307 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 5.9882. Min Range: -5.9882

Max Act: 5.8319. Min Act: -0.1700

Data Index: 189010 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 5.9882. Min Range: -5.9882

Max Act: 5.7382. Min Act: -0.1700

Data Index: 949669 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 5.9882. Min Range: -5.9882

Max Act: 5.7694. Min Act: -0.1700

Data Index: 1284648 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 5.9882. Min Range: -5.9882

Max Act: 5.7694. Min Act: -0.1700

Data Index: 240780 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 5.9882. Min Range: -5.9882

Max Act: 5.7382. Min Act: -0.1700

Data Index: 836100 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 5.9882. Min Range: -5.9882

Max Act: 5.7382. Min Act: -0.1700

Data Index: 122867 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 5.9882. Min Range: -5.9882

Max Act: 5.7382. Min Act: -0.1700

Data Index: 112884 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 5.9882. Min Range: -5.9882

Max Act: 5.6757. Min Act: -0.1700

Data Index: 1282846 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 5.9882. Min Range: -5.9882

Max Act: 5.6757. Min Act: -0.1700

Data Index: 431075 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 5.9882. Min Range: -5.9882

Max Act: 5.7382. Min Act: -0.1700

Data Index: 1298536 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 5.9882. Min Range: -5.9882

Max Act: 5.7069. Min Act: -0.1700

Data Index: 480860 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 5.9882. Min Range: -5.9882

Max Act: 5.6757. Min Act: -0.1700

Data Index: 228377 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 5.9882. Min Range: -5.9882

Max Act: 5.6757. Min Act: -0.1700

Data Index: 1340986 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 5.9882. Min Range: -5.9882

Max Act: 5.7069. Min Act: -0.1700

Data Index: 231853 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 5.9882. Min Range: -5.9882

Max Act: 5.6444. Min Act: -0.1700

Data Index: 1029099 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 5.9882. Min Range: -5.9882

Max Act: 5.7069. Min Act: -0.1700

Data Index: 21642 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 5.9882. Min Range: -5.9882

Max Act: 5.7069. Min Act: -0.1700

Data Index: 956133 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 5.9882. Min Range: -5.9882

Max Act: 5.6132. Min Act: -0.1700

Data Index: 1242371 (C4 (Web Text))

Max Activating Token Index: 672