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

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

Neuron 237 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: 0.1085. Min Range: -0.1085

Max Act: 0.1085. Min Act: -0.0001

Data Index: 590712 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.1050. Min Act: -0.0001

Data Index: 1114885 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.1035. Min Act: -0.0001

Data Index: 381130 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.1004. Min Act: -0.0001

Data Index: 923763 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0983. Min Act: -0.0001

Data Index: 1201305 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0986. Min Act: -0.0001

Data Index: 557487 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.1003. Min Act: -0.0001

Data Index: 824311 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0976. Min Act: -0.0001

Data Index: 359207 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0993. Min Act: -0.0001

Data Index: 1066879 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0971. Min Act: -0.0001

Data Index: 833424 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0972. Min Act: -0.0001

Data Index: 754413 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0965. Min Act: -0.0001

Data Index: 1259168 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0958. Min Act: -0.0001

Data Index: 399930 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0978. Min Act: -0.0001

Data Index: 191613 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0965. Min Act: -0.0001

Data Index: 526993 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0967. Min Act: -0.0001

Data Index: 928307 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0965. Min Act: -0.0001

Data Index: 737616 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0942. Min Act: -0.0001

Data Index: 529412 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0924. Min Act: -0.0001

Data Index: 1272857 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0941. Min Act: -0.0001

Data Index: 163005 (C4 (Web Text))

Max Activating Token Index: 673