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

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

Neuron 5430 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: 0.4566. Min Range: -0.4566

Max Act: 0.4566. Min Act: -0.0001

Data Index: 1274430 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.4070. Min Act: -0.0001

Data Index: 1268022 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.4019. Min Act: -0.0001

Data Index: 961660 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.3904. Min Act: -0.0001

Data Index: 422217 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.3415. Min Act: -0.0001

Data Index: 1187617 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.3295. Min Act: -0.0001

Data Index: 1011360 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.3229. Min Act: -0.0001

Data Index: 106864 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.3164. Min Act: -0.0001

Data Index: 983850 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.3160. Min Act: -0.0001

Data Index: 386824 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.3078. Min Act: -0.0001

Data Index: 775694 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.3151. Min Act: -0.0001

Data Index: 606961 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.3039. Min Act: -0.0001

Data Index: 13852 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.3035. Min Act: -0.0001

Data Index: 528106 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.3110. Min Act: -0.0001

Data Index: 795430 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.3038. Min Act: -0.0001

Data Index: 752487 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.3012. Min Act: -0.0001

Data Index: 41095 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.2953. Min Act: -0.0001

Data Index: 922514 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.3033. Min Act: -0.0001

Data Index: 359601 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.2934. Min Act: -0.0001

Data Index: 489298 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.2960. Min Act: -0.0001

Data Index: 659024 (C4 (Web Text))

Max Activating Token Index: 604