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

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

Neuron 3485 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.4027. Min Act: -0.0001

Data Index: 514855 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.4233. Min Act: -0.0001

Data Index: 454735 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3988. Min Act: -0.0000

Data Index: 49926 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.4225. Min Act: -0.0000

Data Index: 798084 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3784. Min Act: -0.0001

Data Index: 1041657 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3308. Min Act: -0.0000

Data Index: 1004856 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3728. Min Act: -0.0000

Data Index: 1301803 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3589. Min Act: -0.0001

Data Index: 466373 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3463. Min Act: -0.0000

Data Index: 404563 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3546. Min Act: -0.0001

Data Index: 244920 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3533. Min Act: -0.0001

Data Index: 1285486 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3248. Min Act: -0.0001

Data Index: 771134 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.2894. Min Act: -0.0001

Data Index: 741300 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3178. Min Act: -0.0000

Data Index: 606229 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3394. Min Act: -0.0001

Data Index: 875663 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3194. Min Act: -0.0000

Data Index: 1332124 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3070. Min Act: -0.0001

Data Index: 236823 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.2937. Min Act: -0.0001

Data Index: 522632 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3026. Min Act: -0.0001

Data Index: 730427 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3135. Min Act: -0.0000

Data Index: 868116 (C4 (Web Text))

Max Activating Token Index: 535