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

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

Neuron 6116 in Layer 1

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: 0.8957. Min Range: -0.8957

Max Act: 0.8957. Min Act: -0.0002

Data Index: 950626 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.8049. Min Act: -0.0002

Data Index: 105009 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7763. Min Act: -0.0002

Data Index: 1007895 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7437. Min Act: -0.0002

Data Index: 1246762 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7103. Min Act: -0.0002

Data Index: 604229 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7223. Min Act: -0.0002

Data Index: 366790 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7212. Min Act: -0.0002

Data Index: 18989 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7170. Min Act: -0.0002

Data Index: 530349 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7143. Min Act: -0.0002

Data Index: 756040 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7227. Min Act: -0.0002

Data Index: 255456 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6943. Min Act: -0.0002

Data Index: 372610 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.7072. Min Act: -0.0003

Data Index: 832053 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6886. Min Act: -0.0003

Data Index: 698304 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6832. Min Act: -0.0002

Data Index: 1049006 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6826. Min Act: -0.0002

Data Index: 724912 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6924. Min Act: -0.0002

Data Index: 263821 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6830. Min Act: -0.0002

Data Index: 9921 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6681. Min Act: -0.0003

Data Index: 1301933 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6620. Min Act: -0.0002

Data Index: 1327257 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.8957. Min Range: -0.8957

Max Act: 0.6589. Min Act: -0.0002

Data Index: 777965 (C4 (Web Text))

Max Activating Token Index: 704