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

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

Neuron 2032 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: 0.5939. Min Range: -0.5939

Max Act: 0.5939. Min Act: -0.0001

Data Index: 1084065 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.5233. Min Act: -0.0001

Data Index: 871019 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.5169. Min Act: -0.0001

Data Index: 1261661 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.5039. Min Act: -0.0001

Data Index: 374210 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.5039. Min Act: -0.0001

Data Index: 194200 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4894. Min Act: -0.0001

Data Index: 1091129 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4920. Min Act: -0.0001

Data Index: 522329 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4934. Min Act: -0.0001

Data Index: 331898 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4876. Min Act: -0.0002

Data Index: 744631 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4943. Min Act: -0.0001

Data Index: 1235188 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4846. Min Act: -0.0001

Data Index: 956135 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4780. Min Act: -0.0001

Data Index: 54257 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4881. Min Act: -0.0001

Data Index: 21947 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4776. Min Act: -0.0001

Data Index: 742925 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4731. Min Act: -0.0001

Data Index: 332773 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4766. Min Act: -0.0001

Data Index: 1152752 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4742. Min Act: -0.0001

Data Index: 1308385 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4777. Min Act: -0.0001

Data Index: 1036496 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4716. Min Act: -0.0001

Data Index: 624829 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4664. Min Act: -0.0001

Data Index: 1339968 (C4 (Web Text))

Max Activating Token Index: 692