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

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

Neuron 5096 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: 2.1961. Min Range: -2.1961

Max Act: 2.1961. Min Act: -0.0002

Data Index: 456335 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 2.1961. Min Range: -2.1961

Max Act: 2.0327. Min Act: -0.0002

Data Index: 813064 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 2.1961. Min Range: -2.1961

Max Act: 1.8074. Min Act: -0.0002

Data Index: 656799 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 2.1961. Min Range: -2.1961

Max Act: 1.8089. Min Act: -0.0002

Data Index: 375335 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 2.1961. Min Range: -2.1961

Max Act: 1.7863. Min Act: -0.0002

Data Index: 370643 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 2.1961. Min Range: -2.1961

Max Act: 1.6851. Min Act: -0.0002

Data Index: 395936 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 2.1961. Min Range: -2.1961

Max Act: 1.6670. Min Act: -0.0002

Data Index: 905739 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 2.1961. Min Range: -2.1961

Max Act: 1.5749. Min Act: -0.0002

Data Index: 431580 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 2.1961. Min Range: -2.1961

Max Act: 1.5729. Min Act: -0.0002

Data Index: 982282 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 2.1961. Min Range: -2.1961

Max Act: 1.5366. Min Act: -0.0002

Data Index: 872259 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 2.1961. Min Range: -2.1961

Max Act: 1.5059. Min Act: -0.0002

Data Index: 63140 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 2.1961. Min Range: -2.1961

Max Act: 1.5208. Min Act: -0.0002

Data Index: 973412 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 2.1961. Min Range: -2.1961

Max Act: 1.4490. Min Act: -0.0002

Data Index: 1275836 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 2.1961. Min Range: -2.1961

Max Act: 1.4563. Min Act: -0.0002

Data Index: 935429 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 2.1961. Min Range: -2.1961

Max Act: 1.4463. Min Act: -0.0002

Data Index: 1126073 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 2.1961. Min Range: -2.1961

Max Act: 1.4484. Min Act: -0.0003

Data Index: 854365 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 2.1961. Min Range: -2.1961

Max Act: 1.4113. Min Act: -0.0002

Data Index: 673461 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 2.1961. Min Range: -2.1961

Max Act: 1.4096. Min Act: -0.0002

Data Index: 1101959 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 2.1961. Min Range: -2.1961

Max Act: 1.3707. Min Act: -0.0003

Data Index: 508554 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 2.1961. Min Range: -2.1961

Max Act: 1.3892. Min Act: -0.0002

Data Index: 301411 (C4 (Web Text))

Max Activating Token Index: 411