Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3449 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9884. Min Act: -0.0001

Data Index: 1134784 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8953. Min Act: -0.0001

Data Index: 1116959 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9770. Min Act: -0.0001

Data Index: 275568 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9970. Min Act: -0.0000

Data Index: 865961 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9478. Min Act: -0.0001

Data Index: 288939 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9926. Min Act: -0.0001

Data Index: 753069 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8324. Min Act: -0.0001

Data Index: 416906 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8835. Min Act: -0.0001

Data Index: 295019 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8855. Min Act: -0.0001

Data Index: 857976 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9354. Min Act: -0.0001

Data Index: 929728 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9257. Min Act: -0.0001

Data Index: 1116955 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8637. Min Act: -0.0001

Data Index: 1237042 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8593. Min Act: -0.0000

Data Index: 442652 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9206. Min Act: -0.0001

Data Index: 669232 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8793. Min Act: -0.0001

Data Index: 1234953 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8806. Min Act: -0.0001

Data Index: 478711 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8174. Min Act: -0.0001

Data Index: 379905 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8626. Min Act: -0.0001

Data Index: 272727 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8419. Min Act: -0.0001

Data Index: 310197 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8276. Min Act: -0.0001

Data Index: 673400 (C4 (Web Text))

Max Activating Token Index: 339