Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4410 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.8960. Min Act: -0.0000

Data Index: 343970 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.8850. Min Act: -0.0000

Data Index: 1260323 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.8449. Min Act: -0.0000

Data Index: 829879 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.8001. Min Act: -0.0000

Data Index: 425665 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.8168. Min Act: -0.0000

Data Index: 821192 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.8106. Min Act: -0.0000

Data Index: 863155 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7794. Min Act: -0.0000

Data Index: 272094 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7422. Min Act: -0.0000

Data Index: 902416 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7334. Min Act: -0.0000

Data Index: 475608 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7480. Min Act: -0.0000

Data Index: 690587 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7369. Min Act: -0.0000

Data Index: 927781 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7093. Min Act: -0.0000

Data Index: 497914 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7328. Min Act: -0.0000

Data Index: 222355 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7174. Min Act: -0.0000

Data Index: 440075 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7240. Min Act: -0.0000

Data Index: 248033 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7209. Min Act: -0.0000

Data Index: 522937 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6875. Min Act: -0.0000

Data Index: 1128278 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7159. Min Act: -0.0000

Data Index: 1334694 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6861. Min Act: -0.0000

Data Index: 525793 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6861. Min Act: -0.0000

Data Index: 786692 (C4 (Web Text))

Max Activating Token Index: 30