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

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

Neuron 1650 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.7756. Min Act: -0.0001

Data Index: 407174 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.7853. Min Act: -0.0001

Data Index: 1086491 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6572. Min Act: -0.0001

Data Index: 589021 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6559. Min Act: -0.0001

Data Index: 436819 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6309. Min Act: -0.0002

Data Index: 188415 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6423. Min Act: -0.0002

Data Index: 1018161 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6169. Min Act: -0.0001

Data Index: 932672 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5979. Min Act: -0.0001

Data Index: 155720 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6667. Min Act: -0.0002

Data Index: 774707 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6168. Min Act: -0.0001

Data Index: 543322 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6177. Min Act: -0.0001

Data Index: 496199 (C4 (Web Text))

Max Activating Token Index: 761

Text #11

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6147. Min Act: -0.0001

Data Index: 129834 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5668. Min Act: -0.0001

Data Index: 706261 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5808. Min Act: -0.0001

Data Index: 1340403 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6570. Min Act: -0.0001

Data Index: 1321445 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6233. Min Act: -0.0001

Data Index: 1156777 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6353. Min Act: -0.0001

Data Index: 1185352 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5601. Min Act: -0.0002

Data Index: 482639 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6150. Min Act: -0.0001

Data Index: 1037701 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5912. Min Act: -0.0001

Data Index: 1016556 (C4 (Web Text))

Max Activating Token Index: 652