Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1501 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.6753. Min Act: -0.0001

Data Index: 110132 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.6729. Min Act: -0.0001

Data Index: 185975 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.7117. Min Act: -0.0001

Data Index: 1067925 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.6940. Min Act: -0.0001

Data Index: 632855 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.6722. Min Act: -0.0001

Data Index: 729705 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.6261. Min Act: -0.0001

Data Index: 600428 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.6377. Min Act: -0.0001

Data Index: 972219 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.6373. Min Act: -0.0001

Data Index: 1243166 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.6619. Min Act: -0.0001

Data Index: 1357987 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.6084. Min Act: -0.0001

Data Index: 149268 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.5446. Min Act: -0.0001

Data Index: 764031 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.5952. Min Act: -0.0001

Data Index: 915101 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.6001. Min Act: -0.0001

Data Index: 289893 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.6014. Min Act: -0.0001

Data Index: 398725 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.5893. Min Act: -0.0001

Data Index: 834677 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.6050. Min Act: -0.0001

Data Index: 121082 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.5874. Min Act: -0.0001

Data Index: 184736 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.5937. Min Act: -0.0001

Data Index: 31423 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.5055. Min Act: -0.0001

Data Index: 14188 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 0.7117. Min Range: -0.7117

Max Act: 0.5664. Min Act: -0.0001

Data Index: 1294051 (C4 (Web Text))

Max Activating Token Index: 615