Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2874 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.3338. Min Act: -0.0001

Data Index: 894575 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.3288. Min Act: -0.0001

Data Index: 470097 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.2998. Min Act: -0.0001

Data Index: 255378 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.3228. Min Act: -0.0001

Data Index: 875674 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.3533. Min Act: -0.0001

Data Index: 1183274 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.3218. Min Act: -0.0001

Data Index: 212955 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.3059. Min Act: -0.0001

Data Index: 27668 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.2845. Min Act: -0.0001

Data Index: 831084 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.2903. Min Act: -0.0001

Data Index: 51312 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.2970. Min Act: -0.0001

Data Index: 813547 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.3085. Min Act: -0.0001

Data Index: 195712 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.2971. Min Act: -0.0001

Data Index: 143146 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.2925. Min Act: -0.0001

Data Index: 691179 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.3147. Min Act: -0.0001

Data Index: 327530 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.2916. Min Act: -0.0001

Data Index: 1147534 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.2920. Min Act: -0.0001

Data Index: 554075 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.3002. Min Act: -0.0001

Data Index: 147616 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.2760. Min Act: -0.0001

Data Index: 787123 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.2852. Min Act: -0.0001

Data Index: 844539 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 0.3533. Min Range: -0.3533

Max Act: 0.2746. Min Act: -0.0001

Data Index: 807930 (C4 (Web Text))

Max Activating Token Index: 931