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

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

Neuron 350 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: 5.8601. Min Range: -5.8601

Max Act: 5.8601. Min Act: -0.1700

Data Index: 1326858 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 5.8601. Min Range: -5.8601

Max Act: 5.6414. Min Act: -0.1700

Data Index: 402548 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 5.8601. Min Range: -5.8601

Max Act: 5.6257. Min Act: -0.1700

Data Index: 463084 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 5.8601. Min Range: -5.8601

Max Act: 5.5164. Min Act: -0.1700

Data Index: 147644 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 5.8601. Min Range: -5.8601

Max Act: 5.5164. Min Act: -0.1700

Data Index: 765992 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 5.8601. Min Range: -5.8601

Max Act: 5.4695. Min Act: -0.1700

Data Index: 1303511 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 5.8601. Min Range: -5.8601

Max Act: 5.4851. Min Act: -0.1700

Data Index: 325391 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 5.8601. Min Range: -5.8601

Max Act: 5.3914. Min Act: -0.1700

Data Index: 698664 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 5.8601. Min Range: -5.8601

Max Act: 5.4070. Min Act: -0.1700

Data Index: 1188664 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 5.8601. Min Range: -5.8601

Max Act: 5.4070. Min Act: -0.1700

Data Index: 982543 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 5.8601. Min Range: -5.8601

Max Act: 5.3289. Min Act: -0.1700

Data Index: 418602 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 5.8601. Min Range: -5.8601

Max Act: 5.3601. Min Act: -0.1700

Data Index: 13478 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 5.8601. Min Range: -5.8601

Max Act: 5.4070. Min Act: -0.1700

Data Index: 734391 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 5.8601. Min Range: -5.8601

Max Act: 5.2351. Min Act: -0.1700

Data Index: 90712 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 5.8601. Min Range: -5.8601

Max Act: 5.3132. Min Act: -0.1700

Data Index: 267676 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 5.8601. Min Range: -5.8601

Max Act: 5.3445. Min Act: -0.1700

Data Index: 1329520 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 5.8601. Min Range: -5.8601

Max Act: 5.3445. Min Act: -0.1700

Data Index: 536271 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 5.8601. Min Range: -5.8601

Max Act: 5.3289. Min Act: -0.1700

Data Index: 14174 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 5.8601. Min Range: -5.8601

Max Act: 5.2820. Min Act: -0.1700

Data Index: 71933 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 5.8601. Min Range: -5.8601

Max Act: 5.3289. Min Act: -0.1700

Data Index: 349736 (C4 (Web Text))

Max Activating Token Index: 60