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

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

Neuron 939 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1601. Min Range: -3.1601

Max Act: 3.1601. Min Act: -0.0001

Data Index: 298272 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 3.1601. Min Range: -3.1601

Max Act: 2.9985. Min Act: -0.0000

Data Index: 807497 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 3.1601. Min Range: -3.1601

Max Act: 2.7415. Min Act: -0.0001

Data Index: 1254929 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 3.1601. Min Range: -3.1601

Max Act: 2.8575. Min Act: -0.0000

Data Index: 1105538 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 3.1601. Min Range: -3.1601

Max Act: 2.7655. Min Act: -0.0000

Data Index: 1165111 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 3.1601. Min Range: -3.1601

Max Act: 2.4842. Min Act: -0.0001

Data Index: 78389 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 3.1601. Min Range: -3.1601

Max Act: 2.5428. Min Act: -0.0001

Data Index: 301283 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 3.1601. Min Range: -3.1601

Max Act: 2.5273. Min Act: -0.0000

Data Index: 191161 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 3.1601. Min Range: -3.1601

Max Act: 2.4329. Min Act: -0.0001

Data Index: 1358169 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 3.1601. Min Range: -3.1601

Max Act: 2.5178. Min Act: -0.0000

Data Index: 211218 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 3.1601. Min Range: -3.1601

Max Act: 2.2778. Min Act: -0.0000

Data Index: 667197 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 3.1601. Min Range: -3.1601

Max Act: 2.3958. Min Act: -0.0001

Data Index: 1282407 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 3.1601. Min Range: -3.1601

Max Act: 2.2122. Min Act: -0.0000

Data Index: 1128409 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 3.1601. Min Range: -3.1601

Max Act: 2.1964. Min Act: -0.0001

Data Index: 906472 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 3.1601. Min Range: -3.1601

Max Act: 2.2867. Min Act: -0.0000

Data Index: 431044 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 3.1601. Min Range: -3.1601

Max Act: 2.2252. Min Act: -0.0001

Data Index: 795916 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 3.1601. Min Range: -3.1601

Max Act: 2.2023. Min Act: -0.0000

Data Index: 198002 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 3.1601. Min Range: -3.1601

Max Act: 2.1437. Min Act: -0.0000

Data Index: 403562 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 3.1601. Min Range: -3.1601

Max Act: 2.0960. Min Act: -0.0000

Data Index: 427561 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 3.1601. Min Range: -3.1601

Max Act: 2.0999. Min Act: -0.0001

Data Index: 1266128 (C4 (Web Text))

Max Activating Token Index: 511