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

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

Neuron 518 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0601. Min Act: -0.0003

Data Index: 1149305 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0547. Min Act: -0.0002

Data Index: 106951 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0492. Min Act: -0.0003

Data Index: 295654 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0492. Min Act: -0.0003

Data Index: 300043 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0469. Min Act: -0.0003

Data Index: 1143512 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0471. Min Act: -0.0003

Data Index: 135156 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0484. Min Act: -0.0003

Data Index: 968269 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0461. Min Act: -0.0003

Data Index: 360851 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0440. Min Act: -0.0003

Data Index: 1313139 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0451. Min Act: -0.0003

Data Index: 1254455 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0424. Min Act: -0.0003

Data Index: 579756 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0425. Min Act: -0.0003

Data Index: 1309153 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0445. Min Act: -0.0003

Data Index: 980679 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0445. Min Act: -0.0004

Data Index: 156018 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0441. Min Act: -0.0002

Data Index: 247035 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0414. Min Act: -0.0003

Data Index: 580190 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0440. Min Act: -0.0003

Data Index: 1118307 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0422. Min Act: -0.0003

Data Index: 858445 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0391. Min Act: -0.0003

Data Index: 659792 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0394. Min Act: -0.0003

Data Index: 381627 (C4 (Web Text))

Max Activating Token Index: 778