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

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

Neuron 749 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: 1.8944. Min Range: -1.8944

Max Act: 1.8944. Min Act: -0.0001

Data Index: 249639 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.6968. Min Act: -0.0001

Data Index: 1336344 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.6801. Min Act: -0.0001

Data Index: 324318 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.6229. Min Act: -0.0001

Data Index: 1164118 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.4016. Min Act: -0.0001

Data Index: 207840 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.3347. Min Act: -0.0001

Data Index: 811468 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.2636. Min Act: -0.0001

Data Index: 388173 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.2761. Min Act: -0.0001

Data Index: 785918 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.2397. Min Act: -0.0001

Data Index: 932958 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.3100. Min Act: -0.0001

Data Index: 491103 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.2166. Min Act: -0.0001

Data Index: 378310 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.3310. Min Act: -0.0001

Data Index: 344861 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.2280. Min Act: -0.0001

Data Index: 1088107 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.1782. Min Act: -0.0001

Data Index: 876085 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.2196. Min Act: -0.0001

Data Index: 661558 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.1214. Min Act: -0.0001

Data Index: 317692 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.2683. Min Act: -0.0001

Data Index: 666402 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.2093. Min Act: -0.0001

Data Index: 630515 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 1.8944. Min Range: -1.8944

Max Act: 0.9867. Min Act: -0.0001

Data Index: 1052650 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 1.8944. Min Range: -1.8944

Max Act: 1.1523. Min Act: -0.0001

Data Index: 858015 (C4 (Web Text))

Max Activating Token Index: 31