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

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

Neuron 3736 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: 2.8174. Min Range: -2.8174

Max Act: 2.8174. Min Act: -0.0001

Data Index: 897242 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 2.8174. Min Range: -2.8174

Max Act: 2.2052. Min Act: -0.0001

Data Index: 1220370 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 2.8174. Min Range: -2.8174

Max Act: 2.0881. Min Act: -0.0000

Data Index: 83083 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 2.8174. Min Range: -2.8174

Max Act: 2.1399. Min Act: -0.0001

Data Index: 34245 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 2.8174. Min Range: -2.8174

Max Act: 1.8908. Min Act: -0.0000

Data Index: 605039 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 2.8174. Min Range: -2.8174

Max Act: 1.8212. Min Act: -0.0001

Data Index: 187890 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 2.8174. Min Range: -2.8174

Max Act: 1.5882. Min Act: -0.0001

Data Index: 1126656 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 2.8174. Min Range: -2.8174

Max Act: 1.4871. Min Act: -0.0000

Data Index: 65772 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 2.8174. Min Range: -2.8174

Max Act: 1.4088. Min Act: -0.0000

Data Index: 365995 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 2.8174. Min Range: -2.8174

Max Act: 1.4768. Min Act: -0.0001

Data Index: 371724 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 2.8174. Min Range: -2.8174

Max Act: 1.4713. Min Act: -0.0001

Data Index: 608106 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 2.8174. Min Range: -2.8174

Max Act: 1.4681. Min Act: -0.0001

Data Index: 625946 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 2.8174. Min Range: -2.8174

Max Act: 1.4523. Min Act: -0.0001

Data Index: 892007 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 2.8174. Min Range: -2.8174

Max Act: 1.4034. Min Act: -0.0001

Data Index: 283767 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 2.8174. Min Range: -2.8174

Max Act: 1.4083. Min Act: -0.0001

Data Index: 640381 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 2.8174. Min Range: -2.8174

Max Act: 1.3487. Min Act: -0.0000

Data Index: 183882 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 2.8174. Min Range: -2.8174

Max Act: 1.4283. Min Act: -0.0001

Data Index: 337550 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 2.8174. Min Range: -2.8174

Max Act: 1.3341. Min Act: -0.0001

Data Index: 134129 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 2.8174. Min Range: -2.8174

Max Act: 1.3290. Min Act: -0.0001

Data Index: 1208864 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 2.8174. Min Range: -2.8174

Max Act: 1.3349. Min Act: -0.0001

Data Index: 982979 (C4 (Web Text))

Max Activating Token Index: 67