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

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

Neuron 408 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8637. Min Range: -2.8637

Max Act: 2.8637. Min Act: -0.0000

Data Index: 1329401 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 2.8637. Min Range: -2.8637

Max Act: 1.5464. Min Act: -0.0000

Data Index: 176605 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 2.8637. Min Range: -2.8637

Max Act: 1.6933. Min Act: -0.0000

Data Index: 945306 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 2.8637. Min Range: -2.8637

Max Act: 1.4447. Min Act: -0.0000

Data Index: 309252 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 2.8637. Min Range: -2.8637

Max Act: 1.6559. Min Act: -0.0000

Data Index: 352394 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 2.8637. Min Range: -2.8637

Max Act: 1.5518. Min Act: -0.0000

Data Index: 696425 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 2.8637. Min Range: -2.8637

Max Act: 1.5402. Min Act: -0.0000

Data Index: 335400 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 2.8637. Min Range: -2.8637

Max Act: 1.4561. Min Act: -0.0000

Data Index: 1163008 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 2.8637. Min Range: -2.8637

Max Act: 1.5318. Min Act: 0.0000

Data Index: 245587 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 2.8637. Min Range: -2.8637

Max Act: 1.4046. Min Act: -0.0000

Data Index: 591718 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 2.8637. Min Range: -2.8637

Max Act: 1.4700. Min Act: -0.0000

Data Index: 913396 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 2.8637. Min Range: -2.8637

Max Act: 1.3694. Min Act: -0.0000

Data Index: 488792 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 2.8637. Min Range: -2.8637

Max Act: 1.4657. Min Act: -0.0000

Data Index: 842198 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 2.8637. Min Range: -2.8637

Max Act: 1.5753. Min Act: -0.0000

Data Index: 338801 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 2.8637. Min Range: -2.8637

Max Act: 1.5307. Min Act: -0.0000

Data Index: 491423 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 2.8637. Min Range: -2.8637

Max Act: 1.5187. Min Act: -0.0000

Data Index: 769235 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 2.8637. Min Range: -2.8637

Max Act: 1.4177. Min Act: -0.0000

Data Index: 105445 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 2.8637. Min Range: -2.8637

Max Act: 1.4275. Min Act: -0.0000

Data Index: 180032 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 2.8637. Min Range: -2.8637

Max Act: 1.4337. Min Act: -0.0000

Data Index: 103826 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 2.8637. Min Range: -2.8637

Max Act: 1.4670. Min Act: -0.0000

Data Index: 85555 (C4 (Web Text))

Max Activating Token Index: 993