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

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

Neuron 550 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4240. Min Range: -2.4240

Max Act: 2.4240. Min Act: -0.0000

Data Index: 1336731 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 2.4240. Min Range: -2.4240

Max Act: 2.1943. Min Act: -0.0000

Data Index: 192444 (C4 (Web Text))

Max Activating Token Index: 993

Text #2

Max Range: 2.4240. Min Range: -2.4240

Max Act: 1.7478. Min Act: -0.0000

Data Index: 341973 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 2.4240. Min Range: -2.4240

Max Act: 1.5980. Min Act: -0.0000

Data Index: 1342662 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 2.4240. Min Range: -2.4240

Max Act: 1.5433. Min Act: -0.0001

Data Index: 552984 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 2.4240. Min Range: -2.4240

Max Act: 1.5451. Min Act: -0.0000

Data Index: 16936 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 2.4240. Min Range: -2.4240

Max Act: 1.5228. Min Act: -0.0000

Data Index: 842333 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 2.4240. Min Range: -2.4240

Max Act: 1.4162. Min Act: -0.0000

Data Index: 1092192 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 2.4240. Min Range: -2.4240

Max Act: 1.4893. Min Act: -0.0001

Data Index: 1044033 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 2.4240. Min Range: -2.4240

Max Act: 1.3789. Min Act: -0.0000

Data Index: 818463 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 2.4240. Min Range: -2.4240

Max Act: 1.4138. Min Act: -0.0000

Data Index: 1224756 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 2.4240. Min Range: -2.4240

Max Act: 1.3236. Min Act: -0.0001

Data Index: 1157275 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 2.4240. Min Range: -2.4240

Max Act: 1.3725. Min Act: -0.0000

Data Index: 259094 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 2.4240. Min Range: -2.4240

Max Act: 1.3803. Min Act: -0.0000

Data Index: 37122 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 2.4240. Min Range: -2.4240

Max Act: 1.2871. Min Act: -0.0000

Data Index: 506240 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 2.4240. Min Range: -2.4240

Max Act: 1.2696. Min Act: -0.0000

Data Index: 1275214 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 2.4240. Min Range: -2.4240

Max Act: 1.4188. Min Act: -0.0001

Data Index: 1223935 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 2.4240. Min Range: -2.4240

Max Act: 1.3076. Min Act: -0.0000

Data Index: 309066 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 2.4240. Min Range: -2.4240

Max Act: 1.2972. Min Act: -0.0000

Data Index: 534443 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 2.4240. Min Range: -2.4240

Max Act: 1.2101. Min Act: -0.0000

Data Index: 537533 (C4 (Web Text))

Max Activating Token Index: 744