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

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

Neuron 5736 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0938. Min Act: -0.0001

Data Index: 898818 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0921. Min Act: -0.0001

Data Index: 603311 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0928. Min Act: -0.0001

Data Index: 538048 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0903. Min Act: -0.0001

Data Index: 747232 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0917. Min Act: -0.0001

Data Index: 1043806 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0902. Min Act: -0.0002

Data Index: 188858 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0906. Min Act: -0.0001

Data Index: 1317834 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0892. Min Act: -0.0001

Data Index: 127574 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0902. Min Act: -0.0001

Data Index: 405773 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0897. Min Act: -0.0001

Data Index: 1057974 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0876. Min Act: -0.0001

Data Index: 546188 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0880. Min Act: -0.0001

Data Index: 958352 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0870. Min Act: -0.0001

Data Index: 1037766 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0872. Min Act: -0.0001

Data Index: 772850 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0884. Min Act: -0.0001

Data Index: 44996 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0874. Min Act: -0.0002

Data Index: 559574 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0874. Min Act: -0.0001

Data Index: 1216572 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0882. Min Act: -0.0001

Data Index: 1128971 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0855. Min Act: -0.0001

Data Index: 716352 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0874. Min Act: -0.0001

Data Index: 1308201 (C4 (Web Text))

Max Activating Token Index: 257