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

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

Neuron 1612 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: 2.3231. Min Range: -2.3231

Max Act: 2.3231. Min Act: -0.0000

Data Index: 1240527 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 2.3231. Min Range: -2.3231

Max Act: 1.8081. Min Act: -0.0000

Data Index: 878075 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 2.3231. Min Range: -2.3231

Max Act: 1.8801. Min Act: -0.0000

Data Index: 1260412 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 2.3231. Min Range: -2.3231

Max Act: 1.8252. Min Act: -0.0000

Data Index: 773129 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 2.3231. Min Range: -2.3231

Max Act: 1.6394. Min Act: -0.0000

Data Index: 944460 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 2.3231. Min Range: -2.3231

Max Act: 1.5994. Min Act: -0.0000

Data Index: 947683 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 2.3231. Min Range: -2.3231

Max Act: 1.5789. Min Act: -0.0000

Data Index: 222996 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 2.3231. Min Range: -2.3231

Max Act: 1.6982. Min Act: -0.0000

Data Index: 93326 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 2.3231. Min Range: -2.3231

Max Act: 1.6382. Min Act: -0.0000

Data Index: 1308760 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 2.3231. Min Range: -2.3231

Max Act: 1.6314. Min Act: -0.0000

Data Index: 107334 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 2.3231. Min Range: -2.3231

Max Act: 1.5064. Min Act: -0.0000

Data Index: 1018591 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 2.3231. Min Range: -2.3231

Max Act: 1.5731. Min Act: -0.0000

Data Index: 678245 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 2.3231. Min Range: -2.3231

Max Act: 1.3040. Min Act: -0.0000

Data Index: 853068 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 2.3231. Min Range: -2.3231

Max Act: 1.4316. Min Act: -0.0000

Data Index: 951374 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 2.3231. Min Range: -2.3231

Max Act: 1.3968. Min Act: -0.0000

Data Index: 294781 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 2.3231. Min Range: -2.3231

Max Act: 1.5234. Min Act: -0.0000

Data Index: 270621 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 2.3231. Min Range: -2.3231

Max Act: 1.4454. Min Act: -0.0000

Data Index: 472996 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 2.3231. Min Range: -2.3231

Max Act: 1.4473. Min Act: -0.0000

Data Index: 857585 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 2.3231. Min Range: -2.3231

Max Act: 1.4993. Min Act: -0.0000

Data Index: 657503 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 2.3231. Min Range: -2.3231

Max Act: 1.4269. Min Act: -0.0000

Data Index: 1200215 (C4 (Web Text))

Max Activating Token Index: 161