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

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

Neuron 2907 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: 1.5980. Min Range: -1.5980

Max Act: 1.5980. Min Act: -0.0001

Data Index: 1005974 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.5637. Min Act: -0.0001

Data Index: 1210531 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.1647. Min Act: -0.0001

Data Index: 791991 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.2939. Min Act: -0.0001

Data Index: 1236575 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.1638. Min Act: -0.0001

Data Index: 287264 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.0712. Min Act: -0.0001

Data Index: 203104 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.0113. Min Act: -0.0001

Data Index: 1098828 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.0986. Min Act: -0.0001

Data Index: 250930 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 1.5980. Min Range: -1.5980

Max Act: 0.9962. Min Act: -0.0001

Data Index: 949800 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.0570. Min Act: -0.0001

Data Index: 558830 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 1.5980. Min Range: -1.5980

Max Act: 0.9925. Min Act: -0.0001

Data Index: 732645 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 1.5980. Min Range: -1.5980

Max Act: 0.9538. Min Act: -0.0001

Data Index: 439940 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.0666. Min Act: -0.0001

Data Index: 37327 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 1.5980. Min Range: -1.5980

Max Act: 0.9681. Min Act: -0.0001

Data Index: 1250026 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.0146. Min Act: -0.0001

Data Index: 541250 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.0086. Min Act: -0.0001

Data Index: 1219701 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 1.5980. Min Range: -1.5980

Max Act: 0.9964. Min Act: -0.0001

Data Index: 597654 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 1.5980. Min Range: -1.5980

Max Act: 0.9944. Min Act: -0.0001

Data Index: 657622 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 1.5980. Min Range: -1.5980

Max Act: 0.9324. Min Act: -0.0001

Data Index: 893603 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 1.5980. Min Range: -1.5980

Max Act: 0.9942. Min Act: -0.0001

Data Index: 563672 (C4 (Web Text))

Max Activating Token Index: 541