Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4059 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.9927. Min Act: -0.0000

Data Index: 1309477 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.7489. Min Act: -0.0000

Data Index: 383860 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.7398. Min Act: -0.0000

Data Index: 1156942 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.4894. Min Act: -0.0000

Data Index: 563053 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.6301. Min Act: -0.0000

Data Index: 192575 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.5244. Min Act: -0.0000

Data Index: 323788 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.5072. Min Act: -0.0000

Data Index: 552969 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.5876. Min Act: -0.0000

Data Index: 197519 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.4585. Min Act: -0.0000

Data Index: 1072027 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.4374. Min Act: -0.0000

Data Index: 48650 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.3540. Min Act: -0.0000

Data Index: 947162 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.4157. Min Act: -0.0000

Data Index: 1117766 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.4029. Min Act: -0.0000

Data Index: 669884 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.3835. Min Act: -0.0000

Data Index: 211105 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.2946. Min Act: -0.0000

Data Index: 336838 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.4499. Min Act: -0.0000

Data Index: 1179501 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.4340. Min Act: -0.0000

Data Index: 393769 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.2390. Min Act: -0.0000

Data Index: 802805 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.2957. Min Act: -0.0000

Data Index: 1169234 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 1.9927. Min Range: -1.9927

Max Act: 1.2814. Min Act: -0.0000

Data Index: 106066 (C4 (Web Text))

Max Activating Token Index: 861