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

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

Neuron 4047 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.8596. Min Act: -0.0000

Data Index: 323892 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.7744. Min Act: -0.0000

Data Index: 105210 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.7448. Min Act: -0.0001

Data Index: 503025 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.7098. Min Act: -0.0001

Data Index: 554756 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.7073. Min Act: -0.0001

Data Index: 841643 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.6477. Min Act: -0.0000

Data Index: 849903 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.6222. Min Act: -0.0000

Data Index: 66119 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.6122. Min Act: -0.0000

Data Index: 300486 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.6450. Min Act: -0.0000

Data Index: 40242 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.6226. Min Act: -0.0001

Data Index: 829880 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.6220. Min Act: -0.0001

Data Index: 335291 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.5913. Min Act: -0.0000

Data Index: 1185293 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.5816. Min Act: -0.0001

Data Index: 505196 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.6005. Min Act: -0.0000

Data Index: 1152523 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.5899. Min Act: -0.0001

Data Index: 1208209 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.5593. Min Act: -0.0001

Data Index: 801290 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.5209. Min Act: -0.0000

Data Index: 423813 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.5547. Min Act: -0.0000

Data Index: 349668 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.5307. Min Act: -0.0001

Data Index: 444556 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 0.8596. Min Range: -0.8596

Max Act: 0.5450. Min Act: -0.0000

Data Index: 811100 (C4 (Web Text))

Max Activating Token Index: 997