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

Dataset: The Pile

Neuron 2053 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.3442. Min Act: -0.0000

Data Index: 1159055 (The Pile)

Max Activating Token Index: 245

Text #1

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.4037. Min Act: -0.0000

Data Index: 904082 (The Pile)

Max Activating Token Index: 650

Text #2

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.3699. Min Act: -0.0000

Data Index: 369323 (The Pile)

Max Activating Token Index: 920

Text #3

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.3039. Min Act: -0.0000

Data Index: 222870 (The Pile)

Max Activating Token Index: 1004

Text #4

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.3405. Min Act: -0.0000

Data Index: 1814688 (The Pile)

Max Activating Token Index: 213

Text #5

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.3522. Min Act: -0.0000

Data Index: 703538 (The Pile)

Max Activating Token Index: 311

Text #6

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.3435. Min Act: -0.0000

Data Index: 450232 (The Pile)

Max Activating Token Index: 133

Text #7

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.3377. Min Act: -0.0000

Data Index: 1899649 (The Pile)

Max Activating Token Index: 18

Text #8

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.3037. Min Act: -0.0000

Data Index: 1217809 (The Pile)

Max Activating Token Index: 346

Text #9

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.3111. Min Act: -0.0000

Data Index: 153960 (The Pile)

Max Activating Token Index: 180

Text #10

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.3239. Min Act: -0.0000

Data Index: 1057887 (The Pile)

Max Activating Token Index: 58

Text #11

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2900. Min Act: -0.0000

Data Index: 1727420 (The Pile)

Max Activating Token Index: 555

Text #12

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.3245. Min Act: -0.0000

Data Index: 1125932 (The Pile)

Max Activating Token Index: 128

Text #13

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2934. Min Act: -0.0000

Data Index: 1111174 (The Pile)

Max Activating Token Index: 59

Text #14

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.3089. Min Act: -0.0000

Data Index: 405190 (The Pile)

Max Activating Token Index: 201

Text #15

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2657. Min Act: -0.0000

Data Index: 1291925 (The Pile)

Max Activating Token Index: 50

Text #16

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.3069. Min Act: -0.0000

Data Index: 598435 (The Pile)

Max Activating Token Index: 201

Text #17

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2965. Min Act: -0.0000

Data Index: 664757 (The Pile)

Max Activating Token Index: 299

Text #18

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2944. Min Act: -0.0000

Data Index: 51663 (The Pile)

Max Activating Token Index: 590

Text #19

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2936. Min Act: -0.0000

Data Index: 1185341 (The Pile)

Max Activating Token Index: 124