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

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

Neuron 606 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: 1.4313. Min Range: -1.4313

Max Act: 1.2925. Min Act: -0.0001

Data Index: 62705 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.4313. Min Act: -0.0001

Data Index: 955652 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.4192. Min Act: -0.0001

Data Index: 1241294 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.4194. Min Act: -0.0001

Data Index: 421041 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.0930. Min Act: -0.0001

Data Index: 155321 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.1636. Min Act: -0.0001

Data Index: 1195251 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 1.4313. Min Range: -1.4313

Max Act: 0.8822. Min Act: -0.0001

Data Index: 3223 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 1.4313. Min Range: -1.4313

Max Act: 0.9340. Min Act: -0.0001

Data Index: 534354 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.1369. Min Act: -0.0001

Data Index: 507675 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.0461. Min Act: -0.0001

Data Index: 729855 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 1.4313. Min Range: -1.4313

Max Act: 0.9233. Min Act: -0.0001

Data Index: 637420 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.0531. Min Act: -0.0001

Data Index: 572113 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 1.4313. Min Range: -1.4313

Max Act: 0.9879. Min Act: -0.0001

Data Index: 872627 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.0866. Min Act: -0.0001

Data Index: 1159355 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 1.4313. Min Range: -1.4313

Max Act: 0.8818. Min Act: -0.0001

Data Index: 650623 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.0494. Min Act: -0.0001

Data Index: 682076 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.0480. Min Act: -0.0001

Data Index: 776204 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.0787. Min Act: -0.0001

Data Index: 449869 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.0704. Min Act: -0.0001

Data Index: 348306 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 1.4313. Min Range: -1.4313

Max Act: 0.9811. Min Act: -0.0001

Data Index: 381766 (C4 (Web Text))

Max Activating Token Index: 564