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

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

Neuron 3277 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: 0.1061. Min Range: -0.1061

Max Act: 0.1061. Min Act: -0.0001

Data Index: 1136719 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.1037. Min Act: -0.0001

Data Index: 572593 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0941. Min Act: -0.0001

Data Index: 1070251 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0924. Min Act: -0.0001

Data Index: 343488 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0913. Min Act: -0.0001

Data Index: 189941 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0924. Min Act: -0.0001

Data Index: 879535 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0917. Min Act: -0.0001

Data Index: 406513 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0881. Min Act: -0.0001

Data Index: 638803 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0883. Min Act: -0.0001

Data Index: 860820 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0862. Min Act: -0.0001

Data Index: 583519 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0868. Min Act: -0.0001

Data Index: 804607 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0878. Min Act: -0.0001

Data Index: 692311 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0869. Min Act: -0.0001

Data Index: 734857 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0838. Min Act: -0.0001

Data Index: 1124986 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0835. Min Act: -0.0001

Data Index: 477612 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0856. Min Act: -0.0001

Data Index: 828474 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0843. Min Act: -0.0001

Data Index: 1210470 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0850. Min Act: -0.0001

Data Index: 141898 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0837. Min Act: -0.0001

Data Index: 1373662 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0817. Min Act: -0.0001

Data Index: 1309035 (C4 (Web Text))

Max Activating Token Index: 61