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

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

Neuron 4846 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.4782. Min Act: -0.0000

Data Index: 6386 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.4580. Min Act: -0.0000

Data Index: 814527 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.3411. Min Act: -0.0000

Data Index: 747054 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.3841. Min Act: -0.0000

Data Index: 885228 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.3189. Min Act: -0.0000

Data Index: 637459 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.3082. Min Act: -0.0000

Data Index: 14803 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.3139. Min Act: -0.0000

Data Index: 1327828 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.2152. Min Act: -0.0000

Data Index: 252944 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.3250. Min Act: -0.0000

Data Index: 1160909 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.1872. Min Act: -0.0000

Data Index: 333 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.2425. Min Act: -0.0000

Data Index: 1287147 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.3170. Min Act: -0.0000

Data Index: 521792 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.2066. Min Act: -0.0000

Data Index: 1007177 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.1970. Min Act: -0.0000

Data Index: 1023309 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.3466. Min Act: -0.0000

Data Index: 477605 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.1884. Min Act: -0.0000

Data Index: 423362 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.1978. Min Act: -0.0000

Data Index: 710280 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.2480. Min Act: -0.0000

Data Index: 1107666 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.1854. Min Act: -0.0000

Data Index: 112823 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 1.4782. Min Range: -1.4782

Max Act: 1.1849. Min Act: -0.0000

Data Index: 597135 (C4 (Web Text))

Max Activating Token Index: 662