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

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

Neuron 1937 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.2586. Min Range: -3.2586

Max Act: 3.2586. Min Act: -0.0000

Data Index: 500834 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 3.2586. Min Range: -3.2586

Max Act: 3.0559. Min Act: -0.0000

Data Index: 701004 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 3.2586. Min Range: -3.2586

Max Act: 2.7079. Min Act: -0.0000

Data Index: 372968 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 3.2586. Min Range: -3.2586

Max Act: 3.2095. Min Act: -0.0000

Data Index: 1152775 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 3.2586. Min Range: -3.2586

Max Act: 2.8556. Min Act: -0.0000

Data Index: 263985 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 3.2586. Min Range: -3.2586

Max Act: 2.7124. Min Act: -0.0000

Data Index: 450316 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 3.2586. Min Range: -3.2586

Max Act: 2.6795. Min Act: -0.0000

Data Index: 12190 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 3.2586. Min Range: -3.2586

Max Act: 2.6138. Min Act: -0.0000

Data Index: 180901 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 3.2586. Min Range: -3.2586

Max Act: 2.4602. Min Act: -0.0000

Data Index: 1222331 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 3.2586. Min Range: -3.2586

Max Act: 2.3921. Min Act: -0.0000

Data Index: 1365523 (Python Code)

Max Activating Token Index: 294

Text #10

Max Range: 3.2586. Min Range: -3.2586

Max Act: 2.5180. Min Act: -0.0000

Data Index: 1184292 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 3.2586. Min Range: -3.2586

Max Act: 2.3734. Min Act: -0.0000

Data Index: 213012 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 3.2586. Min Range: -3.2586

Max Act: 2.4462. Min Act: -0.0000

Data Index: 1205383 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 3.2586. Min Range: -3.2586

Max Act: 2.4574. Min Act: -0.0000

Data Index: 818040 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 3.2586. Min Range: -3.2586

Max Act: 2.3331. Min Act: -0.0000

Data Index: 699059 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 3.2586. Min Range: -3.2586

Max Act: 2.2027. Min Act: -0.0000

Data Index: 1087270 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 3.2586. Min Range: -3.2586

Max Act: 2.3011. Min Act: -0.0000

Data Index: 19793 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 3.2586. Min Range: -3.2586

Max Act: 2.2934. Min Act: -0.0000

Data Index: 49538 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 3.2586. Min Range: -3.2586

Max Act: 2.2602. Min Act: -0.0000

Data Index: 172734 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 3.2586. Min Range: -3.2586

Max Act: 2.2502. Min Act: -0.0000

Data Index: 1285263 (C4 (Web Text))

Max Activating Token Index: 724