Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1582 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.4119. Min Act: -0.0000

Data Index: 988111 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3978. Min Act: -0.0000

Data Index: 536425 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3857. Min Act: -0.0000

Data Index: 154082 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3399. Min Act: -0.0000

Data Index: 363240 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3220. Min Act: -0.0000

Data Index: 278966 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3439. Min Act: -0.0000

Data Index: 894009 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3307. Min Act: -0.0000

Data Index: 350841 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3402. Min Act: -0.0000

Data Index: 754075 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3292. Min Act: -0.0000

Data Index: 832247 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3189. Min Act: -0.0000

Data Index: 895896 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3219. Min Act: -0.0000

Data Index: 639670 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3279. Min Act: -0.0000

Data Index: 594871 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3362. Min Act: -0.0000

Data Index: 220345 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3327. Min Act: -0.0000

Data Index: 866034 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3096. Min Act: -0.0000

Data Index: 634056 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3073. Min Act: -0.0000

Data Index: 1169832 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3112. Min Act: -0.0000

Data Index: 1017492 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3091. Min Act: -0.0000

Data Index: 363017 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.3115. Min Act: -0.0000

Data Index: 90261 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 0.4119. Min Range: -0.4119

Max Act: 0.2866. Min Act: -0.0000

Data Index: 1205193 (C4 (Web Text))

Max Activating Token Index: 24