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

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

Neuron 2208 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.2395. Min Range: -7.2395

Max Act: 7.2395. Min Act: -0.0001

Data Index: 1308121 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 7.2395. Min Range: -7.2395

Max Act: 7.0157. Min Act: -0.0001

Data Index: 1151386 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 7.2395. Min Range: -7.2395

Max Act: 6.6367. Min Act: -0.0001

Data Index: 93624 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 7.2395. Min Range: -7.2395

Max Act: 6.2313. Min Act: -0.0001

Data Index: 174191 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 7.2395. Min Range: -7.2395

Max Act: 6.7592. Min Act: -0.0001

Data Index: 201661 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 7.2395. Min Range: -7.2395

Max Act: 6.1538. Min Act: -0.0001

Data Index: 950848 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 7.2395. Min Range: -7.2395

Max Act: 6.8320. Min Act: -0.0001

Data Index: 1133212 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 7.2395. Min Range: -7.2395

Max Act: 5.8915. Min Act: -0.0001

Data Index: 642868 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 7.2395. Min Range: -7.2395

Max Act: 5.5754. Min Act: -0.0001

Data Index: 206900 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 7.2395. Min Range: -7.2395

Max Act: 5.6159. Min Act: -0.0001

Data Index: 1118500 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 7.2395. Min Range: -7.2395

Max Act: 4.9131. Min Act: -0.0001

Data Index: 1047494 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 7.2395. Min Range: -7.2395

Max Act: 5.2075. Min Act: -0.0001

Data Index: 1066342 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 7.2395. Min Range: -7.2395

Max Act: 4.8636. Min Act: -0.0001

Data Index: 816387 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 7.2395. Min Range: -7.2395

Max Act: 5.2107. Min Act: -0.0001

Data Index: 71850 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 7.2395. Min Range: -7.2395

Max Act: 4.9732. Min Act: -0.0001

Data Index: 499451 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 7.2395. Min Range: -7.2395

Max Act: 4.7524. Min Act: -0.0001

Data Index: 23719 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 7.2395. Min Range: -7.2395

Max Act: 4.4767. Min Act: -0.0001

Data Index: 1034826 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 7.2395. Min Range: -7.2395

Max Act: 4.3985. Min Act: -0.0001

Data Index: 688901 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 7.2395. Min Range: -7.2395

Max Act: 4.2131. Min Act: -0.0001

Data Index: 795211 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 7.2395. Min Range: -7.2395

Max Act: 4.1350. Min Act: -0.0001

Data Index: 839270 (C4 (Web Text))

Max Activating Token Index: 552