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

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

Neuron 1909 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.4224. Min Act: -0.0001

Data Index: 1310531 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3806. Min Act: -0.0001

Data Index: 963123 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3484. Min Act: -0.0001

Data Index: 895247 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3328. Min Act: -0.0001

Data Index: 890355 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3433. Min Act: -0.0001

Data Index: 737139 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3071. Min Act: -0.0001

Data Index: 743549 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3101. Min Act: -0.0001

Data Index: 415647 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3076. Min Act: -0.0001

Data Index: 229157 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3056. Min Act: -0.0001

Data Index: 1335602 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.2758. Min Act: -0.0001

Data Index: 973030 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.2435. Min Act: -0.0001

Data Index: 1070780 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.2925. Min Act: -0.0001

Data Index: 799032 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.2921. Min Act: -0.0001

Data Index: 31522 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3121. Min Act: -0.0001

Data Index: 556473 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.3027. Min Act: -0.0001

Data Index: 293432 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.2782. Min Act: -0.0001

Data Index: 964290 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.2910. Min Act: -0.0001

Data Index: 719305 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.2710. Min Act: -0.0001

Data Index: 586385 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.2986. Min Act: -0.0001

Data Index: 1093664 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 0.4224. Min Range: -0.4224

Max Act: 0.2936. Min Act: -0.0001

Data Index: 937202 (C4 (Web Text))

Max Activating Token Index: 925