Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 620 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.1102. Min Range: -1.1102

Max Act: 1.1102. Min Act: -0.0002

Data Index: 1354328 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 1.1102. Min Range: -1.1102

Max Act: 1.0690. Min Act: -0.0003

Data Index: 452725 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 1.1102. Min Range: -1.1102

Max Act: 1.0573. Min Act: -0.0002

Data Index: 758512 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 1.1102. Min Range: -1.1102

Max Act: 1.0534. Min Act: -0.0002

Data Index: 1154944 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 1.1102. Min Range: -1.1102

Max Act: 1.0330. Min Act: -0.0002

Data Index: 1165199 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 1.1102. Min Range: -1.1102

Max Act: 1.0216. Min Act: -0.0002

Data Index: 1357392 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 1.1102. Min Range: -1.1102

Max Act: 1.0170. Min Act: -0.0002

Data Index: 1327902 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 1.1102. Min Range: -1.1102

Max Act: 1.0163. Min Act: -0.0002

Data Index: 1042890 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 1.1102. Min Range: -1.1102

Max Act: 1.0108. Min Act: -0.0002

Data Index: 170638 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.9888. Min Act: -0.0002

Data Index: 563019 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.9739. Min Act: -0.0002

Data Index: 994158 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.9983. Min Act: -0.0002

Data Index: 1055094 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.9571. Min Act: -0.0002

Data Index: 1281578 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.9707. Min Act: -0.0002

Data Index: 75032 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.9883. Min Act: -0.0002

Data Index: 527143 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.9688. Min Act: -0.0002

Data Index: 618331 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.9725. Min Act: -0.0002

Data Index: 186532 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.9627. Min Act: -0.0002

Data Index: 1236908 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.9522. Min Act: -0.0002

Data Index: 353924 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 1.1102. Min Range: -1.1102

Max Act: 0.9582. Min Act: -0.0002

Data Index: 960312 (C4 (Web Text))

Max Activating Token Index: 381