Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3287 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.4598. Min Act: -0.0001

Data Index: 782608 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3430. Min Act: -0.0001

Data Index: 310655 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3424. Min Act: -0.0001

Data Index: 426921 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3267. Min Act: -0.0001

Data Index: 1075112 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3379. Min Act: -0.0001

Data Index: 723012 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3338. Min Act: -0.0001

Data Index: 158080 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3255. Min Act: -0.0001

Data Index: 1140494 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3046. Min Act: -0.0001

Data Index: 1348665 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3155. Min Act: -0.0001

Data Index: 23875 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3070. Min Act: -0.0001

Data Index: 235391 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3217. Min Act: -0.0001

Data Index: 837224 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3020. Min Act: -0.0001

Data Index: 829450 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3151. Min Act: -0.0001

Data Index: 901409 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3001. Min Act: -0.0001

Data Index: 1192737 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3056. Min Act: -0.0001

Data Index: 168018 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3079. Min Act: -0.0001

Data Index: 559322 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3078. Min Act: -0.0001

Data Index: 505909 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.2977. Min Act: -0.0001

Data Index: 934955 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3048. Min Act: -0.0001

Data Index: 1271192 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 0.4598. Min Range: -0.4598

Max Act: 0.3048. Min Act: -0.0001

Data Index: 142560 (C4 (Web Text))

Max Activating Token Index: 632