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

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

Neuron 2828 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2523. Min Act: -0.0001

Data Index: 1196845 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2305. Min Act: -0.0002

Data Index: 1312706 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2195. Min Act: -0.0002

Data Index: 1244311 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2244. Min Act: -0.0002

Data Index: 771439 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2146. Min Act: -0.0001

Data Index: 507207 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2128. Min Act: -0.0001

Data Index: 953908 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1956. Min Act: -0.0002

Data Index: 546470 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2117. Min Act: -0.0002

Data Index: 311460 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2068. Min Act: -0.0002

Data Index: 732873 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2084. Min Act: -0.0002

Data Index: 1096427 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2020. Min Act: -0.0001

Data Index: 1223650 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2036. Min Act: -0.0001

Data Index: 273457 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1889. Min Act: -0.0001

Data Index: 745352 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2002. Min Act: -0.0001

Data Index: 510102 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1894. Min Act: -0.0001

Data Index: 1000090 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.2008. Min Act: -0.0001

Data Index: 671335 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1969. Min Act: -0.0001

Data Index: 440035 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1837. Min Act: -0.0002

Data Index: 1055431 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1835. Min Act: -0.0001

Data Index: 146829 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 0.2523. Min Range: -0.2523

Max Act: 0.1868. Min Act: -0.0001

Data Index: 1330527 (C4 (Web Text))

Max Activating Token Index: 892