Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3473 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3965. Min Act: -0.0000

Data Index: 1048981 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3853. Min Act: -0.0000

Data Index: 332146 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3541. Min Act: -0.0001

Data Index: 150244 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3591. Min Act: -0.0000

Data Index: 1081854 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3496. Min Act: -0.0000

Data Index: 858419 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3364. Min Act: -0.0000

Data Index: 1291738 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3500. Min Act: -0.0001

Data Index: 173611 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3171. Min Act: -0.0000

Data Index: 1137241 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3238. Min Act: -0.0000

Data Index: 1066102 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3297. Min Act: -0.0000

Data Index: 833677 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3170. Min Act: -0.0000

Data Index: 496407 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3106. Min Act: -0.0001

Data Index: 1071058 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2993. Min Act: -0.0000

Data Index: 1031212 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3322. Min Act: -0.0000

Data Index: 1217821 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3027. Min Act: -0.0000

Data Index: 1194080 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2857. Min Act: -0.0000

Data Index: 353189 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.3040. Min Act: -0.0000

Data Index: 248713 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2638. Min Act: -0.0000

Data Index: 387552 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2740. Min Act: -0.0000

Data Index: 1018645 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 0.3965. Min Range: -0.3965

Max Act: 0.2824. Min Act: -0.0000

Data Index: 107619 (C4 (Web Text))

Max Activating Token Index: 359