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

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

Neuron 228 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.8942. Min Act: -0.1700

Data Index: 730185 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.8785. Min Act: -0.1700

Data Index: 297914 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.8942. Min Act: -0.1700

Data Index: 1109461 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.8629. Min Act: -0.1700

Data Index: 1211702 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.8316. Min Act: -0.1700

Data Index: 1339339 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.8003. Min Act: -0.1700

Data Index: 261140 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.8003. Min Act: -0.1700

Data Index: 1106985 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.8160. Min Act: -0.1700

Data Index: 741153 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7847. Min Act: -0.1700

Data Index: 1156045 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.8160. Min Act: -0.1700

Data Index: 705314 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7847. Min Act: -0.1700

Data Index: 808770 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7847. Min Act: -0.1700

Data Index: 1178393 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.8160. Min Act: -0.1700

Data Index: 1089663 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7534. Min Act: -0.1700

Data Index: 14702 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7847. Min Act: -0.1700

Data Index: 691841 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7534. Min Act: -0.1700

Data Index: 134705 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7847. Min Act: -0.1700

Data Index: 967713 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7847. Min Act: -0.1700

Data Index: 286375 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7847. Min Act: -0.1700

Data Index: 718167 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.8003. Min Act: -0.1700

Data Index: 45563 (C4 (Web Text))

Max Activating Token Index: 295