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

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

Neuron 2252 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4956. Min Act: -0.0001

Data Index: 1506201 (Python Code)

Max Activating Token Index: 546

Text #1

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4342. Min Act: -0.0001

Data Index: 90584 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4003. Min Act: -0.0001

Data Index: 573184 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3950. Min Act: -0.0001

Data Index: 749139 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3802. Min Act: -0.0001

Data Index: 68707 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3831. Min Act: -0.0001

Data Index: 1539600 (Python Code)

Max Activating Token Index: 617

Text #6

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3736. Min Act: -0.0001

Data Index: 981359 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4453. Min Act: -0.0001

Data Index: 417542 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3595. Min Act: -0.0001

Data Index: 1496365 (Python Code)

Max Activating Token Index: 198

Text #9

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3583. Min Act: -0.0001

Data Index: 341187 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3531. Min Act: -0.0001

Data Index: 857754 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3422. Min Act: -0.0001

Data Index: 1016097 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3035. Min Act: -0.0001

Data Index: 1639881 (Python Code)

Max Activating Token Index: 635

Text #13

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3477. Min Act: -0.0001

Data Index: 1182374 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3873. Min Act: -0.0001

Data Index: 922132 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3466. Min Act: -0.0001

Data Index: 1132811 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3732. Min Act: -0.0001

Data Index: 1321322 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3392. Min Act: -0.0001

Data Index: 978850 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.2980. Min Act: -0.0001

Data Index: 1240717 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4120. Min Act: -0.0001

Data Index: 648793 (C4 (Web Text))

Max Activating Token Index: 685