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

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

Neuron 448 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: 5.0548. Min Range: -5.0548

Max Act: 5.0548. Min Act: -0.1700

Data Index: 567085 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 5.0548. Min Range: -5.0548

Max Act: 5.0548. Min Act: -0.1700

Data Index: 1077882 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 5.0548. Min Range: -5.0548

Max Act: 4.9923. Min Act: -0.1700

Data Index: 356470 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 5.0548. Min Range: -5.0548

Max Act: 4.9923. Min Act: -0.1700

Data Index: 125358 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 5.0548. Min Range: -5.0548

Max Act: 4.9298. Min Act: -0.1700

Data Index: 479392 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 5.0548. Min Range: -5.0548

Max Act: 4.8985. Min Act: -0.1700

Data Index: 1332779 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 5.0548. Min Range: -5.0548

Max Act: 4.8360. Min Act: -0.1700

Data Index: 781427 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 5.0548. Min Range: -5.0548

Max Act: 4.8360. Min Act: -0.1700

Data Index: 521430 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 5.0548. Min Range: -5.0548

Max Act: 4.9610. Min Act: -0.1700

Data Index: 816042 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 5.0548. Min Range: -5.0548

Max Act: 4.7735. Min Act: -0.1700

Data Index: 426932 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 5.0548. Min Range: -5.0548

Max Act: 4.7110. Min Act: -0.1700

Data Index: 978690 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 5.0548. Min Range: -5.0548

Max Act: 4.7110. Min Act: -0.1700

Data Index: 475059 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 5.0548. Min Range: -5.0548

Max Act: 4.6485. Min Act: -0.1700

Data Index: 127188 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 5.0548. Min Range: -5.0548

Max Act: 4.6172. Min Act: -0.1700

Data Index: 673151 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 5.0548. Min Range: -5.0548

Max Act: 4.5235. Min Act: -0.1700

Data Index: 107432 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 5.0548. Min Range: -5.0548

Max Act: 4.5860. Min Act: -0.1700

Data Index: 141143 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 5.0548. Min Range: -5.0548

Max Act: 4.5547. Min Act: -0.1700

Data Index: 433406 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 5.0548. Min Range: -5.0548

Max Act: 4.4922. Min Act: -0.1700

Data Index: 1162098 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 5.0548. Min Range: -5.0548

Max Act: 4.5235. Min Act: -0.1700

Data Index: 1163096 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 5.0548. Min Range: -5.0548

Max Act: 4.4922. Min Act: -0.1700

Data Index: 753872 (C4 (Web Text))

Max Activating Token Index: 478