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

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

Neuron 3602 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1324. Min Range: -1.1324

Max Act: 1.1324. Min Act: -0.0001

Data Index: 1332270 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 1.1324. Min Range: -1.1324

Max Act: 1.0748. Min Act: -0.0000

Data Index: 475030 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.9323. Min Act: -0.0000

Data Index: 1145175 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8998. Min Act: -0.0000

Data Index: 964673 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.9005. Min Act: -0.0001

Data Index: 1161057 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8949. Min Act: -0.0000

Data Index: 744153 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8889. Min Act: -0.0001

Data Index: 1071183 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.9132. Min Act: -0.0000

Data Index: 743314 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8526. Min Act: -0.0000

Data Index: 546555 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8843. Min Act: -0.0000

Data Index: 28917 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8369. Min Act: -0.0001

Data Index: 365666 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8169. Min Act: -0.0000

Data Index: 720838 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.7944. Min Act: -0.0001

Data Index: 581160 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8155. Min Act: -0.0001

Data Index: 641060 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8145. Min Act: -0.0001

Data Index: 323898 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.7892. Min Act: -0.0001

Data Index: 789581 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8120. Min Act: -0.0001

Data Index: 400242 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8034. Min Act: -0.0000

Data Index: 632095 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8001. Min Act: -0.0000

Data Index: 966004 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 1.1324. Min Range: -1.1324

Max Act: 0.8041. Min Act: -0.0001

Data Index: 985432 (C4 (Web Text))

Max Activating Token Index: 827