Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2400 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0050. Min Range: -2.0050

Max Act: 1.9359. Min Act: -0.0000

Data Index: 1053690 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 2.0050. Min Range: -2.0050

Max Act: 1.9955. Min Act: -0.0000

Data Index: 719878 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 2.0050. Min Range: -2.0050

Max Act: 1.9717. Min Act: -0.0000

Data Index: 28046 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 2.0050. Min Range: -2.0050

Max Act: 2.0050. Min Act: -0.0000

Data Index: 443139 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 2.0050. Min Range: -2.0050

Max Act: 1.7294. Min Act: -0.0000

Data Index: 732889 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 2.0050. Min Range: -2.0050

Max Act: 1.8046. Min Act: -0.0000

Data Index: 302147 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 2.0050. Min Range: -2.0050

Max Act: 1.8003. Min Act: -0.0000

Data Index: 997804 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 2.0050. Min Range: -2.0050

Max Act: 1.8068. Min Act: -0.0000

Data Index: 398363 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 2.0050. Min Range: -2.0050

Max Act: 1.7835. Min Act: -0.0000

Data Index: 500080 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 2.0050. Min Range: -2.0050

Max Act: 1.7755. Min Act: -0.0000

Data Index: 1042316 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 2.0050. Min Range: -2.0050

Max Act: 1.7620. Min Act: -0.0000

Data Index: 1016271 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 2.0050. Min Range: -2.0050

Max Act: 1.7450. Min Act: -0.0000

Data Index: 33649 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 2.0050. Min Range: -2.0050

Max Act: 1.8357. Min Act: -0.0000

Data Index: 905414 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 2.0050. Min Range: -2.0050

Max Act: 1.7333. Min Act: -0.0000

Data Index: 70728 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 2.0050. Min Range: -2.0050

Max Act: 1.6172. Min Act: -0.0000

Data Index: 336955 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 2.0050. Min Range: -2.0050

Max Act: 1.6157. Min Act: -0.0000

Data Index: 334607 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 2.0050. Min Range: -2.0050

Max Act: 1.4423. Min Act: -0.0000

Data Index: 1015147 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 2.0050. Min Range: -2.0050

Max Act: 1.7087. Min Act: -0.0000

Data Index: 501532 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 2.0050. Min Range: -2.0050

Max Act: 1.7571. Min Act: -0.0000

Data Index: 1321636 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 2.0050. Min Range: -2.0050

Max Act: 1.7810. Min Act: -0.0000

Data Index: 537241 (C4 (Web Text))

Max Activating Token Index: 442