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

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

Neuron 131 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0951. Min Range: -2.0951

Max Act: 2.0885. Min Act: -0.0000

Data Index: 308707 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 2.0951. Min Range: -2.0951

Max Act: 2.0951. Min Act: -0.0000

Data Index: 299705 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 2.0951. Min Range: -2.0951

Max Act: 1.8164. Min Act: -0.0000

Data Index: 727262 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 2.0951. Min Range: -2.0951

Max Act: 1.7312. Min Act: -0.0000

Data Index: 185348 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 2.0951. Min Range: -2.0951

Max Act: 1.6552. Min Act: -0.0000

Data Index: 289336 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 2.0951. Min Range: -2.0951

Max Act: 1.5653. Min Act: -0.0000

Data Index: 925759 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 2.0951. Min Range: -2.0951

Max Act: 1.4803. Min Act: -0.0000

Data Index: 716271 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 2.0951. Min Range: -2.0951

Max Act: 1.5085. Min Act: -0.0000

Data Index: 995146 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 2.0951. Min Range: -2.0951

Max Act: 1.4886. Min Act: -0.0000

Data Index: 252858 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 2.0951. Min Range: -2.0951

Max Act: 1.4720. Min Act: -0.0000

Data Index: 990099 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 2.0951. Min Range: -2.0951

Max Act: 1.4766. Min Act: -0.0000

Data Index: 1034374 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 2.0951. Min Range: -2.0951

Max Act: 1.3969. Min Act: -0.0000

Data Index: 670701 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 2.0951. Min Range: -2.0951

Max Act: 1.4145. Min Act: -0.0000

Data Index: 1192368 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 2.0951. Min Range: -2.0951

Max Act: 1.4106. Min Act: -0.0000

Data Index: 99287 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 2.0951. Min Range: -2.0951

Max Act: 1.3244. Min Act: -0.0000

Data Index: 1010833 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 2.0951. Min Range: -2.0951

Max Act: 1.3797. Min Act: -0.0000

Data Index: 1140926 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 2.0951. Min Range: -2.0951

Max Act: 1.2813. Min Act: -0.0000

Data Index: 726464 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 2.0951. Min Range: -2.0951

Max Act: 1.3229. Min Act: -0.0000

Data Index: 484642 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 2.0951. Min Range: -2.0951

Max Act: 1.3820. Min Act: -0.0000

Data Index: 1268079 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 2.0951. Min Range: -2.0951

Max Act: 1.2924. Min Act: -0.0000

Data Index: 232843 (C4 (Web Text))

Max Activating Token Index: 418